Role-playing with large language models is fundamentally a session-level task, requiring agents to sustain character identity and interaction quality across extended multi-turn conversations. Yet existing evaluation and optimization methods remain largely turn-level, failing to capture long-horizon quality. We propose DynSess, a unified session-level framework for role-playing agents. DynSess-Eval scores complete dialogue sessions via rubrics targeting long-horizon behaviors. Leveraging its session-level rewards, we construct high-quality training trajectories through multi-turn lookahead search and train DynSess-Character with two complementary variants: DSPO (off-policy) and GSRPO (on-policy). Experiments show that DynSess-Eval aligns with human judgments substantially better than prior evaluators, and blind human evaluation further shows that DynSess-Character matches the strongest character model despite using substantially fewer parameters, while maintaining strong role consistency and interactive ability. Our dataset and code will be released to facilitate future research.

Symmetry is a central organizing principle in natural systems, yet its use as a unifying design strategy in robotics has largely remained limited to geometric form. We show that symmetry can instead be leveraged at the level of dynamic actuation capability. We introduce dynamic symmetry, the uniformity of a robot's attainable center-of-mass accelerations, and formalize it through a measure coined as dynamic isotropy. Across more than 1000 simulated morphologies, we found that higher dynamic symmetry consistently improved trajectory tracking, task success, robustness, resiliency, and energy efficiency, with the benefits becoming most pronounced as dynamic isotropy approached its theoretical limit. To study this regime systematically, we developed Argus, a family of spherical robots designed to explore the effects of increasing dynamic symmetry. Members of the Argus family vary in their actuation geometry and dynamic symmetry level while sharing a common architectural principle: radially oriented linear actuators that directly shape the robot's center-of-mass dynamics. Among them, we built a physical 20-leg Argus variant that achieved near-extreme dynamic isotropy and demonstrated orientation-invariant locomotion, agile traversal of cluttered and deformable terrain, rapid self-stabilization, and resilience to partial actuator failures. Its distributed sensing further enabled omnidirectional perception and object interaction during continuous motion. These results show that designing robots for symmetry not only in morphology but also in their attainable dynamics provides a powerful and general pathway toward agility, robustness, and multifunctionality in uncertain terrestrial and extraterrestrial environments.

Task success can hide process anomalies in real-world agent executions. An agent may pass the final task oracle while still accumulating unresolved ambiguity, unsafe external writes, ignored errors, weakly grounded commitments, or capability-boundary overcommitment. We study this mismatch as the Outcome-Process Gap and introduce OpenClawBench, a large-scale dataset for measuring and supervising process-side anomalies in real agent execution processes. OpenClawBench is built from BFCL-driven OpenClaw sessions produced by 6 source models and contains 31,264 annotated trajectories. It aligns task-oracle outcomes with structured process evidence. FullTax converts the aligned trajectories into structured anomaly supervision: binary labels, supporting evidence, onset/span localization, severity, recoverability, and a 5-class anomaly taxonomy. Using OpenClawBench, we make the Outcome-Process Gap measurable. Among 31,135 oracle-passing executions, 2,904 are still labeled process-anomalous under FullTax. These results show that success-only evaluation misses a concrete class of process-side failures in real agent executions. A LoRA-fine-tuned Gemma 3 12B detector trained on the high-confidence FullTax supervised pool reaches binary F1=0.729 on the cleaner-labels held-out test split. Together, OpenClawBench turns real agent execution logs into auditable and reusable supervision for studying, diagnosing, and operationally monitoring runtime agent reliability.

As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in artificial intelligence security. Existing defense architectures heavily rely on empirical semantic guardrails and probabilistic large model adjudicators, mechanisms that fail to provide deterministic security lower bounds when facing complex semantic symbol decoupling attacks. To overcome this empirical semantic guardrail dilemma, this paper proposes a new security paradigm for agents based on the fundamental limitations of logical reasoning. Based on this paradigm, we further introduce an executable Proof-Constrained Action (ePCA) framework with a neural symbolic isolation architecture. This framework abandons semantic trust in natural language, forcing agents to losslessly formalize their intentions into first-order logical mathematical constraints before performing physical operations. Empirical evaluations of macroscopic and microscopic two-dimensional dynamic adversarial systems demonstrate that our formal verification mechanism achieves zero attack success rate and zero false positive rate across the evaluated scenarios, with extremely low computational latency. This research provides a conditional formal foundation under explicit system assumptions and an engineering paradigm for constructing the underlying defense foundation for future intelligent systems.

Real-world information needs require access to structurally diverse knowledge sources, from unstructured text and relational tables to knowledge graphs and property graphs. Existing retrievers, however, operate over one source at a time under a fixed query language, leaving the broader landscape of available knowledge fragmented behind incompatible interfaces. A natural attempt at unification would collapse these sources into a shared space, but this erases the structural affordances (such as schemas, ontologies, compositional operators) that give each source its expressive power. Effective retrieval over diverse knowledge, therefore, requires not homogenization but an overarching layer that meets each source on its own terms. To achieve this, we present OmniRetrieval, a framework that takes any natural-language query, identifies appropriate knowledge sources, and dispatches source-native queries to their native execution engines. Across an extensive benchmark spanning 13 datasets and 309 distinct knowledge bases over text, relational, and graph-structured sources, OmniRetrieval exceeds single-source baselines, demonstrating that it can serve as a general-purpose interface to the heterogeneous sources while preserving the structural distinctions that make each source valuable.

Large language models (LLMs) demonstrate strong chain-of-thought (CoT) reasoning abilities, while smaller models (<= 3B parameters) significantly underperform on multi-step reasoning tasks. Based on empirical analyses of the Qwen-2.5 model family on math reasoning benchmarks, we find that more proficient reasoning is associated with fewer reasoning steps but higher information density per step, a property we term Dense Reasoning. Motivated by this observation, we propose DenseSteer, a training-free inference-time steering framework that enhances small-model reasoning by modulating internal representations toward dense reasoning patterns. Experiments show that our method yields consistent accuracy improvements without increasing token-level Negative Log-Likelihood, highlighting dense reasoning as an effective structural approach to mathematical problem solving.

Forecasting conversational derailment is the task of predicting, as the conversation unfolds, whether it will eventually derail into personal attacks. Since forecasting models operate in an online fashion, they must decide whether to "trigger" an alert after each utterance--for example, to notify participants or a moderator that the conversation is at risk of derailing. Existing approaches make this decision solely based on the estimated likelihood of derailment given the preceding utterances, implicitly assuming that the conversation's future trajectory is fixed. As a result, they ignore the possibility of future recovery and incur an unnecessarily high rate of false positives. In this work we propose a method for decoupling the decision to trigger from derailment likelihood estimation. Our approach is inspired by the first human baseline on this task, which shows that humans achieve dramatically lower false positive rates by selectively deferring their decision to trigger when they anticipate that tension is likely to subside. We operationalize this insight with a deferral mechanism that uses forward-looking simulations to assess whether a tense moment admits plausible paths to recovery. Incorporating this mechanism into a state-of-the-art forecasting model substantially reduces false positives without sacrificing forecasting accuracy. More broadly, this work highlights the value of treating decision-making as a first-class component of forecasting systems.

AI-augmented classrooms generate rich teacher and student feedback before graded outcomes become available, yet these signals can be difficult to translate into timely instructional decisions. We propose an interpretable decision layer: a transparent mechanism that ranks course topics requiring attention without using grades or post-hoc outcome labels. The approach combines three signals: student learning difficulty prevalence, disagreement between learner self-reports and observed difficulties, and unresolved teacher concerns. The output is a ranked set of topic priorities with per-topic decision records explaining each ranking. In one graduate CS course offering ($n=5$ instructor interviews; $n=279$ survey responses), prioritized topics aligned with instructor concerns (top-5 overlap 3/5; Spearman $ρ=0.80$) and student-reported topic difficulty ($ρ=0.46$, $p=.048$). Multi-signal integration also surfaced learners not identified through individual signal sources alone (AUC $=0.96$ vs. $0.91$ for gap prevalence alone). Reflective thinking, help-seeking, and self-efficacy provided additional evidence that student behavioral signals align with learning-related constructs. While preliminary, these findings suggest that transparent coordination mechanisms may help support human-AI co-agency when feedback is incomplete.

Alarm fatigue in intensive care units (ICUs) is a well documented patient safety crisis. Clinical monitors generate 350 or more alarms per patient per day, out of which 72-99% are clinically irrelevant. Staff desensitization to non-actionable alarms increases the risk of missed true emergencies. This paper presents SigmaMedStat, a machine learning system that evaluates the trustworthiness of physiological alarm signals before clinical action is taken. Four approaches were evaluated on the PhysioNet/Computing in Cardiology Challenge 2015 dataset of 498 four-channel ICU alarm recordings. Primary contribution is a temporal modeling framework that splits each 60 second recording into six consecutive 10-second chunks, and this in turn generates Continuous Wavelet Transform (CWT) scalograms per chunk, encodes each chunk with a shared EfficientNet-B0 encoder, and passes the resulting feature sequence to a two-layer Long Short-Term Memory (LSTM) network. Five-fold stratified cross-validation yields a mean AUC of 0.822 +/- 0.016 (95% CI: [0.790,0.853]), compared to 0.641 for a static EfficientNet baseline trained on the full 60-second window. Ablation studies confirm that temporal chunking and multi-channel signal fusion both contribute independently to classification performance. Per-alarm type analysis reveals that Ventricular Flutter is the most accurately classified alarm type (AUC 0.820) while Asystole remains the hardest (AUC 0.722). Error analysis identifies 65 false negatives and 85 high-confidence misclassifications as the primary failure modes. All code and results are publicly available at https://github.com/Arun-K-Ram/sigmamedstat.

We study large-scale literature search from two complementary angles: improving the retrieval pipeline, and stress-testing the human reference list as an evaluation target. First, we implement a Deep Research pipeline that processes the full query paper and expands the retrieved results breadth-first along their bibliographies, and show that it substantially outperforms vanilla API-only search, raising recall on RollingEval-Jun25 (a 250-paper literature-search benchmark) from below 20% to above 80%. Second, we use a neutral LLM-as-a-judge to determine if human references are sound ground truth for the task. We find significant limitations: only 51% of human citations are judged moderately relevant or higher, against 86--88% for the strongest AI-based re-rankers. We study this gap on the OpenAlex co-authorship graph, finding that humans are 2.5x more likely than the best AI re-rankers to cite a direct collaborator. Together, our results argue against single-axis literature-search evaluation: recall, topical-relevance scoring, ranked-list diversity, and a co-authorship-distance diagnostic each measure complementary properties of citation quality and should be reported jointly.

Age estimation from facial images typically relies on training data that includes images of minors, a practice that raises serious ethical, legal, and privacy concerns. In this work, we propose a generalized zero-shot benchmark for facial age estimation that explicitly excludes children's data during training while still assessing model performance on younger populations. We revisit six widely used datasets and introduce standardized splits with strict age-group separation: samples aged 18-59 for training, validation, and testing; samples under 18 reserved exclusively for zero-shot evaluation; and samples 60+ as an unseen validation set for model selection under distribution shift. For datasets with identity annotations, subject-exclusive splits prevent identity leakage and better reflect real-world deployment conditions. Evaluating nine state-of-the-art age estimation methods under this protocol reveals that all evaluated methods consistently fail to generalize to unseen age groups, suffering substantial performance degradation -- on average 46.4%, and up to 52.8% -- relative to the supervised baseline. Moreover, models do not simply degrade: they systematically anchor predictions for unseen ages to nearby seen classes, a manifestation of the well-known seen-class bias in generalized zero-shot learning. By formalizing age estimation without children's data as a generalized zero-shot benchmark on existing datasets, this work highlights a critical gap between current modeling practices and real-world ethical constraints. Our benchmark provides a principled basis for evaluating models under restricted data regimes and encourages the development of methods that are robust to distribution shift and aligned with responsible data use.

Reasoning distillation transfers complex reasoning abilities from large language models (LLMs) to smaller ones, yet its success depends on how well the training data align with the student model. This paper introduces the Data-Model Compatibility (DMC) metric, which can be used to assess the suitability of a dataset for reasoning distillation on a student model. DMC provides an assessment by jointly considering data quality, relative difficulty, and student capability. We validated the effectiveness of DMC from two perspectives: (1) DMC exhibits a strong correlation with reasoning distillation performance; and (2) using DMC as the criterion for data selection leads to improved reasoning distillation performance. Both findings are consistently demonstrated across multiple student models and tasks. Moreover, since the DMC of each dataset dynamically changes during training, our experiments demonstrate that dynamically selecting datasets based on DMC can further enhance performance.

Self-evolving agents improve over time by reflecting on past failures, but existing evaluation is limited in two ways: it measures only task scores, leaving reflection quality unknown, and it relies on agents' own episode runs, offering no mechanism to target specific failure patterns. We present \textbf{BenchTrace}, a benchmark for evaluating self-evolution ability in LLM agents. BenchTrace is built on a snapshot-reflection dataset of 1,821 annotated episodes spanning six diverse tasks, and comprises a \textbf{Reflection Evaluation} that probes failure identification through targeted QA tasks, and an \textbf{Evolution Evaluation} that tests whether past failure experience translates into avoidance behavior in a controlled self-evolution simulation. Building on BenchTrace, we propose \textbf{failure avoidance rate (FAR)}, a new evaluation metric measuring the fraction of test cases in which the agent successfully avoids the target failure instance. Experiments with Qwen3-32B and GPT-4.1 reveal that both models fall below a 30\% end-to-end pass rate on reflection evaluation, with diagnosis as the primary bottleneck. Evolution evaluation shows that self-evolution methods generally improve FAR over the non-evolving baseline, but agents forget early lessons as noise episodes accumulate, and agents fail to generalize their reflections beyond the specific context, causing negative transfer across task contexts. Our correlation analysis further reveals that only a fully correct reflection is strongly associated with higher FAR. BenchTrace exposes concrete limits of current self-evolution approaches and provides a controlled, model-agnostic framework for targeted evaluation.

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms that govern model outputs. Prior work shows that enabling retrieval in agents increases compliance with harmful requests. We introduce AgentREVEAL, a diagnostic framework for analyzing retrieval-induced safety degradation in LLM agents. The framework examines two axes: how retrieval is integrated into the agent pipeline and the properties of the retrieved content. Along the integration axis, we find that binding tool invocation and response generation in a single step amplifies harmful outputs. Along the content axis, we uncover the Safe Source Paradox: even oppositional or safety-oriented sources, such as pages containing warnings or risk disclaimers, can increase harmful compliance by an average of 25% compared to the no-retrieval baseline. Finally, we show that relevance acts as a shared activation condition for both vulnerabilities. Similar patterns appear on frontier closed models, and harmful compliance remains elevated under several representative pipeline interventions, with some agents also entering this regime under autonomous retrieval. Because relevance is also what makes retrieval useful, these results expose a safety-utility trade-off for retrieval-enabled agents. We introduce HarmURLBench, a benchmark containing 1,405 real-world URLs paired with 320 harmful behaviors to support future evaluations.

Thyroid cancer is said to be the second most common type of cancer in female individuals and the third in males by 2030, according to projections. In general, detecting cancer in its early stages improves the chance of survival of the individual. Thermography is a diagnostic tool that has been increasingly used to detect cancer and abnormalities, including that of thyroid. Various methods to segment and detect hot regions in thermograms and, consequently, to detect suspicious tissues present in these images have been proposed. It is well known that medical diagnosis yields a great deal of information. Thus, physicians have to comprehensively analyse and evaluate this information in a short period of time, which is infeasible in most cases. In this work, we perform a general review of thermography , focusing on the thyroid analysis. We propose protocols for image acquisiton and an autonomous registration for thyroid images. We also perform analyses of the image data, which include feature extraction, image processing, and a possible approach for classification of healthy or unhealthy patients. In summary, this work presents a pilot project for detection of tumors in our university hospital, which is part of an effort to support preventive medical actions in our endocrinology department. Under some future adjustments, this project will be submitted for approval by the ethics and research committee of Hospital Universitário Antonio Pedro at Universidade Federal Fluminense (HUAP-UFF) and to the Brazilian Ministry of Health Ethical committee under the name: Evaluation of the importance of thermography to aid diagnosis of thyroid nodules of patients in HUAP-UFF (in Portuguese: Avaliação da importância da termografia no auxílio à investigação diagnóstica de nódulos tireoidianos em pacientes acompanhados no HUAP-UFF).

Tracking the dynamics of non-canonical biological systems in microscopy videos remains a persistent challenge. Both classical and learning-based trackers depend on expert-reviewed data to be evaluated and adapted, yet exhaustive manual annotation rarely scales to the videos where these tools are needed most. We developed RIPPLE (Refinement Interpolation Platform for Point Location Estimation), which recasts annotation as sparse correction: a user clicks a starting point, RIPPLE proposes a full trajectory, and the user intervenes only where the trajectory drifts. We tested RIPPLE on five challenging microscopy datasets from our laboratories, four from the transparent jellyfish Clytia hemisphaerica and one tracking landmarks on rapidly moving sperm. Across these, RIPPLE matched the quality of exhaustive manual annotation while reducing manual clicks by 3 to 25 times across datasets. RIPPLE thereby fills a missing layer between manual annotation and fully automated tracking, enabling immediate quantification of biological dynamics, method benchmarking, and the production of the gold-standard data needed to adapt future automated microscopy trackers.

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely manually constructed, providing only coarse start-goal annotations without intermediate trajectories, while recent automatic generation efforts remain expensive, biased, and shallow. These limitations prevent reliable training and evaluation of agents that must generalize to realistic, multi-hop, cross-page tasks. We introduce a scalable framework, GTA, that integrates crawling, retrieval-based seeding, in-context generation, and automated quality control to produce realistic tasks paired with executable trajectories. This design decouples crawling from generation for greater efficiency, grounds tasks in the site graph to enforce compositionality, and ensures dense supervision through deterministic replays and systematic validation. We instantiate the pipeline on over 50 websites covering e-commerce, government, forums, and news, with multilingual and multi-hop coverage. The resulting benchmark reveals a significant human-agent performance gap and enables detailed diagnostics. Our contributions are three-fold: (i) formalizing multi-hop web-agent task generation, (ii) proposing an efficient and validated pipeline for automatic data creation, and (iii) releasing a dynamic benchmark with reproducible evaluation.

The amount of fat on the surroundings of the heart is correlated to several health risk factors such as carotid stiffness, coronary artery calcification, atrial fibrillation, atherosclerosis, cancer incidence and others. Furthermore, the cardiac fat varies unrelated to the overall fat of the subject, and, therefore, it reinforces the quantitative analysis of these adipose tissues as being essential. Clinical decision support systems are computer programs capable of evaluating information and providing a corresponding diagnosis or data to complement the physicists' analyses. The aim of this work is to propose a method capable of fully automatically segmenting two types of cardiac adipose tissues that stand apart from each other by the pericardium on CT images obtained by the standard acquisition protocol used for coronary calcium scoring. Much effort was devoted to promote minimal user intervention and ease of reproducibility. The methodology proposed in this work consists of a registration, which will roughly adjust input images to a standard, an extraction of features related to pixels and their surrounding area and a segmentation step based on data mining classification algorithms that define if an incoming pixel is of a certain type. Experimentations showed that the achieved mean accuracy for the epicardial and mediastinal fats was 98.4% with a mean true positive rate of 96.2%. In average, the Dice similarity index was equal to 96.8%.

Image quality in modern imaging systems emerges from the coupled effects of the sensor, optics, and computational reconstruction. Ultra-thin metalenses offer a path toward substantial miniaturization of optical modules, but practical designs often exhibit pronounced chromatic and field-dependent aberrations that necessitate computational reconstruction. In current metalens pipelines, reconstruction models are commonly trained and selected using distortion-based fidelity objectives, such as PSNR, yet these proxies can be weakly correlated with human preference and downstream utility, reflecting the well-known perception--distortion trade-off. We introduce MetaRanker, a human-in-the-loop active ranking framework that formalizes metalens image quality in terms of semantic interpretability, defined as the degree to which humans can reliably recognize objects and structures in the presence of optical artifacts. MetaRanker combines a probabilistic preference model with uncertainty-aware query selection, and leverages vision--language models to provide lightweight semantic priors. Importantly, these priors are used only to guide the sampling of informative comparisons; human judgments remain the primary supervision signal throughout. Across real-world and synthetic metalens datasets with distinct degradation profiles, MetaRanker produces rankings that align most closely with human assessments, while reducing the number of pairwise annotations required by approximately 80% relative to exhaustive pairwise evaluation. Finally, we show that standard image quality assessment metrics exhibit limited alignment with human interpretability in the metalens domain, positioning MetaRanker as a practical step toward perceptually grounded metalens evaluation and co-design.

Recent advances in text-to-music generation enable high-fidelity synthesis of structured musical audio, raising growing concerns about data provenance, consent, and training transparency. These models are typically trained on large-scale corpora with little disclosure, leaving no practical mechanism to verify whether a particular audio sample was included in training. In this paper, we investigate black-box membership inference for generative music models, aiming to determine whether a candidate music sample was used during training, given only query access to the deployed system. Our key insight is that training membership induces systematically stronger semantic and structural alignment between a candidate sample and the model's generation conditioned on its caption. We query the target model with the associated caption and measure the relationship between the candidate audio and the generated output in a learned feature space. To capture features that separate members from non-members, we construct paired examples consisting of each track and its caption-conditioned generation from shadow models, and train a music auditor to classify membership. The auditor captures alignment patterns characteristic of training membership and generalizes to unseen target models in a fully black-box setting without access to model parameters or training metadata. Across multiple state-of-the-art music generators, our method achieves up to 98.6% accuracy, with false-positive and false-negative rates as low as 1.9% and 1.0%, demonstrating that reliable training-data auditing is feasible in realistic deployment scenarios.

Many stochastic physical systems evolve smoothly over time in the sense that the distribution of states changes regularly across time steps. The transition from current state to the next state can often be modeled as the combination of a smooth map and an explicit source of randomness. Stochastic Lifting exploits this structure by attaching an independent, high-dimensional random label to each state transition in the training data and fitting a transition map from the current state and label to the next state using a standard regression loss. The labels act as auxiliary coordinates that let the model represent multiple plausible next states from similar current states, avoiding collapse to a mean prediction in the finite-sample size regime. At inference, fresh labels are sampled at each time step and the learned map is rolled forward autoregressively, generating diverse trajectories with a single network evaluation per time step.

Chain-of-thought traces from large reasoning models can span tens of thousands of tokens, yet we lack a vocabulary for describing their internal structure. Previous methods developed to analyze chain-of-thought traces are either too rigid or not expressive enough, failing to capture features across domains and models. To remedy this, we develop ReasonOps, an unsupervised, expressive method for annotating chain-of-thought traces, providing succinct universal operators. Using ReasonOps, we analyze 44,662 traces from 12 thinking LLMs spanning 6 families across 8 reasoning benchmarks and discover that they share a common compositional structure: 7 recurring reasoning operators -- discourse-level moves such as backtracking, inferring, and hypothesizing -- that emerge from unsupervised clustering of sentence-initial 3-token pivots. These operators appear across every model family and benchmark domain, confirmed by three independent LLM judges who classify held-out samples at 70 -76% accuracy. We analyze the structure of operators on easy vs. hard problems, revealing that reflective operators are more helpful on hard problems and harm performance on easy problems. Operator sequences are highly model-identifying: a classifier trained on operator distributions alone recovers the source model with macro-AUC, revealing that each model family has a distinctive reasoning fingerprint. Structural operator features predict within-problem answer correctness well above baselines. Classifiers built on these operators reach WP-AUC and on AIME specifically. ReasonOps further enables early quality estimation well before the trace completes: we predict at WP-AUC for only 50% of the trace. The ReasonOps pipeline is unsupervised and annotation-free, enabling deep insights into LLM reasoning traces as well as strong downstream results on model identification and correctness prediction.

Reinforcement learning using verifiable rewards (RLVR) improves LLM reasoning, but the conditions under which it transfers across domains -- and why it does so -- remain under-explored. We study cross-domain transfer in a 7B model whose SFT and RL post-training stages use only constraint-satisfaction puzzles, with no mathematics problems in the post-training data. To analyze how transfer emerges, we introduce a reasoning primitive-level framework that combines a 9-class span classifier with motif extraction, allowing us to segment chain-of-thought traces into primitive motifs and track their evolution across training stages and domains. We find that puzzle SFT induces a reasoning-primitive vocabulary, yielding a $+7$pp \texttt{pass@32} gain on OlymMATH-Hard. Vanilla GSPO then composes these primitives into longer compute-verify chains, adding a further $+6$pp. However, this RL stage also suppresses exploratory primitives such as \textit{hypothesize} and \textit{backtrack}. To address this, we introduce a novelty bonus that rewards diverse correct rollouts, using perplexity under the reference model as a signal. This restores recovery primitives during RL and adds a further $+7$pp \texttt{pass@32} relative to vanilla GSPO. Finally, the end-to-end recipe raises the hard-math capability ceiling from $16.0\%$ at the OLMo3-7B-Instruct-SFT base to $36.0\%$, without adding any mathematics problems during the SFT or RL stages.

Dictionary methods, topic models, and embedding-similarity scorers are widely used in CSS and management research to measure constructs such as "entrepreneurial spirit" in corporate speeches. We contribute a label-light measurement diagnostic for such instruments rather than a new extraction model. On a corpus of 80 speeches by leaders of centrally administered Chinese state-owned enterprises, we exploit a natural experiment of 24 same-company different-speaker pairs and 5 same-company same-speaker pairs to test whether a method's per-document indices vary with leader identity holding firm constant. LDA fails (Cohen d=0.20, 95% CI [-0.72, 1.20]); a dictionary scorer reaches d=0.81 and a Chinese sentence encoder d=0.65 on doc-vector distances of order 10^-3. A zero-shot 9B open-weight LLM (Qwen3.5:9b) raises paired-contrast d to 1.09 (exact permutation p1=0.034). We downgrade three claims accordingly: gold F1 measures consistency with the LLM's own prompt rule rather than external construct recovery; doc-level style residualisation cuts the LLM's d to 0.43 (p1=0.22), so roughly half of the effect is consistent with leader idiolect; and a confidence-weighted calibration trades Delta for variance with an auto-mined slogan lexicon near-inert in ablation. We release the 2,190-segment scored corpus, the 170-paragraph pilot, the slogan lexicon, two-family LLM scores, and the evaluation harness.

Large Language Models (LLMs) offer a promising avenue for scientific discovery, yet their application to symbolic regression is often constrained by inefficient search strategies and coarse feedback signals. Current methods typically guide LLMs using scalar metrics (e.g., global Mean Squared Error), which fail to identify which components of a proposed equation are driving performance or causing error. We introduce \textit{Influence-Guided Symbolic Regression} (IGSR), a method that frames equation discovery as an iterative two-step process combining diverse term generation with rigorous selection: an LLM generates candidate basis functions $ψ_j(\mathbf{x})$ for a linear model, which are then evaluated using granular influence scores $Δ_j$. These scores quantify each term's marginal contribution to generalization accuracy, enabling an influence-guided pruning process that systematically refines the model structure. Integrating this mechanism into a Monte Carlo Tree Search (MCTS) enables navigating the combinatorial search space while balancing exploration of novel functional forms with exploitation of high-influence components. We demonstrate IGSR's effectiveness on a diverse suite of benchmarks, including LLM-SRBench, pharmacological PKPD models, an epidemiological simulation, and real-world genomic data. Notably, we validate the framework's capacity for genuine discovery in a case study using a high-dimensional biological dataset, in which IGSR identified a novel relationship between DNA methylation and RNA Polymerase II pausing; a hypothesis that was subsequently supported via wet-lab experimentation.

DeFi investment agents, systems that use AI for autonomous on-chain trading, have attained over USD 3 billion in combined token valuations since late 2024. We survey over 1,900 AI-tagged crypto projects, filter to investment-focused agents, and curate 10 representative projects spanning strategy and observability dimensions. We then conduct a deep-dive architectural analysis of two prominent agent frameworks, ElizaOS and Virtuals Protocol, and a quantitative on-chain performance analysis of 11 Solana-based agent treasuries with publicly attributable trading activity, covering 925,323 token holders. We find that current deployments remain early and heterogeneous: (1) in our sample, many projects do not yet provide clear evidence of autonomous trade execution, and developer interviews suggest that many visible deployments remain basic API integrations; (2) agent treasuries retain over USD 30M in paper gains while token holders collectively lost USD 191.7M, with the top 1% of wallets capturing 81.4% of all gains (USD 1.81B); (3) token valuations are weakly connected to treasury fundamentals, with market-cap-to-AUM ratios exceeding 10,000x versus below 1x for established DeFi protocols; and (4) aggregate user gains peaked at USD 2.4B before declining to net losses, with median returns negative on every platform and tokens declining 93% on average from all-time highs. We interpret these outcomes as characteristic of a permissionless, first-generation market in which open infrastructure enables rapid experimentation but also allows naive or speculative agents to launch before robust standards for autonomy, performance, and stakeholder alignment emerge. We therefore propose a maturity framework along three dimensions: autonomous execution, risk-adjusted profitability, and stakeholder alignment, to characterize the gap between current deployments and future investment-grade agent systems.

Seasonal climate predictions support planning and risk management by offering early information of the most likely-to-occur climate conditions in the coming months, and associated uncertainties. Ensemble forecasts enable this by simulating many plausible outcomes, allowing predictions to be expressed as usable probabilities. Large ensembles and high-resolution forecasts strengthen this guidance by better sampling uncertainty and capturing finer-scale processes but come with significant computational cost. Moreover, forecast ensembles drift and exhibit systematic biases and spatio-temporal errors that grow with lead time, requiring careful post-processing and calibration. A probabilistic post-processing framework based on conditional Variational Autoencoders (cVAEs) was developed at the Canadian Center for Climate Modeling and Analysis to generate large ensembles of bias adjusted seasonal predictions of Arctic sea ice. The generative model was designed to learn the observational distribution conditioned on the biased model prediction. This enables generation of arbitrarily large ensembles of well-calibrated, bias corrected forecasts with improved skill. Here, we extend this framework to address the loss of fine-scale energy and the characteristic blurriness in predictions, a known limitation of standard cVAEs. Specifically, we employ a generator in place of the Gaussian parametrized decoder in the cVAE and use Continuous Ranked Probability Score in the objective function instead of the Mean Square Error. We further use a higher resolution target dataset compared to the raw forecast. We show that the adjusted forecasts are better calibrated, more consistent with the observational distribution, and exhibit smaller errors than benchmark predictions, while also enhancing the resolution of the raw forecasts and improving sharpness and spectral power relative to the standard cVAE.

Legal NLP benchmarks are overwhelmingly English-centric, leaving failure modes in morphologically rich, non-Latin-script languages undetected. We introduce UA-Legal-Bench, a five-task benchmark for evaluating large language models on Ukrainian legal reasoning, built from the Unified State Register of Court Decisions (EDRSR) -- one of the world's largest open judicial corpora (99.5 million decisions). The benchmark comprises: (1) case-type classification (4 classes, n=2,000), (2) judgment form classification (4 classes, n=2,000), (3) case-outcome prediction (6 classes, n=800), (4) legal norm extraction (n=1,794), and (5) cause category prediction (22 classes, n=1,871). We evaluate 11 LLMs (3B--675B) from five families under zero-shot and 3-shot prompting via AWS Bedrock with 158K API calls. Our results reveal sharply task-dependent few-shot effects: few-shot prompting improves judgment form classification by up to +38.6 pp but has mixed effects on outcome prediction. We show that accuracy is misleading on imbalanced legal tasks: the model with highest COP accuracy (62%) is a majority-class predictor (macro-F1: 23%), while the genuinely best model scores only 44% macro-F1. Within-family scaling analysis reveals that 8B models can match frontier performance on surface-level tasks but scaling thresholds vary dramatically across families. We release all data, prompts, and model predictions.

Question answering (QA) is a core challenge in AI, particularly for complex queries requiring multi-hop reasoning across documents, or symbolic operations like aggregation or exhaustive listing. Retrieval-augmented generation has become the dominant approach to QA, with recent graph-based variants addressing part of these issues by organizing knowledge to better support compositional questions. However, most textual graph-based RAG methods still lack the structure needed for symbolic operations useful to answer complex questions reliably. This motivates symbolic graph-based approaches, which extract knowledge graphs (KGs) whose relations are logic predicates that enable SQL-like querying. Yet these pipelines typically use LLMs for KG extraction, which can introduce consistency issues, where extracted facts may violate commonsense ontology constraints. We propose a neuro-symbolic framework for ontology-grounded KG construction combining open-domain extraction, embedding-based canonicalization of types and predicates, and targeted LLM-based correction of ontology violations. By deferring corrections to a post-extraction stage, our method avoids repeated LLM calls, substantially reducing token usage while improving KG consistency and preserving downstream QA quality. Finally, we show that the extracted KGs are well suited for symbolic querying by measuring the occurrence of SPARQL graph patterns.

Generating realistic graph-structured data is challenging due to discrete connectivity, varying graph sizes, and class-specific structural patterns. Recent Generative Adversarial Networks (GAN)-based graph generation methods improve edge modelling by learning connectivity and matching class-specific density distributions. However these models still exhibit noticeable deviations such as in degree and spectral distribution when compared to real graphs, indicating that important structural properties are not fully preserved. This work aims to reduce these deviations by refining the graphs produced by an existing GAN-based graph generator framework with a Genetic Algorithm (GA). In the GAN framework, the generator produces both node features and connectivity patterns, while a GNN-based critic evaluates graph realism and class consistency to ensure global structural and class alignment. Building on this foundation, we apply a GA to refine the edges of generated graphs. The refinement process guides synthetic graphs toward closer agreement with real data, while preserving diversity and novelty. Experimental results show that the GA refinement consistently lowers combined Maximum Mean Discrepancy (MMD) compared to the base model, leading to graphs that more closely match real structural patterns. This demonstrates that evolutionary refinement is an effective and flexible way to correct residual structural deviations in GAN-based graph generators, improving their suitability for realistic graph synthesis and data augmentation.