Data-driven engineering design is constrained by the lack of large-scale 3D datasets that pair geometry with physics-based performance labels. In particular, existing 3D data augmentation techniques have limitations in preserving subtle and diverse geometric variations, and it remains difficult to automate the subsequent simulation-labeling process, where boundary conditions vary depending on the generated geometry. We present DeepJEB++, a foundation-model-driven data-augmentation framework that expands a small seed set of jet engine brackets into a large, simulation-labeled 3D dataset under constrained resources. Our key idea is to augment in the data-rich 2D latent space, then transfer to 3D. In Stage 1, we fine-tune a pretrained 2D latent diffusion model on multi-view renders and synthesize novel views by latent interpolation, retaining manufacturable designs through a vision-language-model (VLM) quality filter. In Stage 2, the validated images are lifted to 3D meshes by a domain-adapted generative foundation model. In Stage 3, an automated pipeline recognizes the load and bolt interfaces on each mesh and assigns finite-element labels -- mass, stress, and displacement -- without manual intervention. We assess augmentation quality along three intrinsic axes: manufacturability, label fidelity against the SimJEB ground truth, and distributional consistency. Starting from fewer than 400 seed designs, DeepJEB++ yields 15,360 simulation-labeled 3D brackets -- a 40x expansion -- using a single GPU per stage. The dataset will be made publicly available to support reproducible engineering-AI research.

Cyclic peptides represent a promising class of therapeutic compounds in modern drug discovery, often offering improved stability and binding affinity. However, the de novo design of cyclic peptides remains challenging because methods must identify pocket-adaptive cyclization patterns and linkage sites while simultaneously controlling drug-relevant properties. This challenge is particularly pronounced for recent generative models trained predominantly on linear peptide data, which may fail to capture cyclization-specific constraints. To address the limitation, we introduce APCyc, a target-aware de novo cyclic peptide generation framework that explicitly models cyclization and jointly optimizes multiple essential physicochemical properties. By using an expanded residue vocabulary and explicitly encoding cyclization-site and linkage-type information, APCyc learns cyclization-aware representations and leverages Bayesian posterior guidance to steer sampling toward cyclic peptides satisfying multiple property objectives. Experimental results demonstrate that our model learns target-dependent cyclization preferences, and enables effective and controllable multi-property optimization for cyclic peptide design. The source code of this paper is available at this https URL.

Recursive multi-step forecasting is usually framed as distribution shift: models are trained on observed histories but deployed on their own predictions. We show this framing is incomplete by proving that, under partial observability or state truncation, recursive rollout is also an epistemic underidentification problem. Even with deterministic latent dynamics, one-step Bayes supervision identifies behavior only on observed contexts and need not identify the deployed recursive predictor once rollout queries self-generated induced states whose correct local targets are not determined by numeric state alone. We formalize this with induced states $Z$ and provenance variables $P$, and derive a decomposition of induced-state error into teacher-forcing/rollout mismatch, representation--class approximation, and provenance information gaps. Empirically, we show that rollout enters a distinct induced-state regime, that fixed induced states define a distinct local corrective task, and that closed-loop gains arise not only from local adaptation but also from changing the induced states visited during rollout. Using a simple binary provenance encoding, provenance-aware correction can further improve performance, though gains are conditional rather than uniform. These results recast exposure bias as reasoning under self-induced epistemic uncertainty.

Action-conditioned world models let an autonomous vehicle predict future camera scenes from its own planned controls, enabling planning and simulation without real-world rollouts, but at compact, trainable scale the futures are ambiguous and the field's standard distortion metrics actively mislead: they reward a blurry regression mean over a realistic prediction. We confront this with a compact latent world model that, given the present front-camera latent and a sequence of ego-actions, predicts future scene latents a frozen decoder renders to $256 \times 256$ frames up to 8 seconds ahead, evaluated on 150 held-out nuScenes scenes. We first benchmark where to predict: across six frozen encoders spanning four representation families, V-JEPA2 with temporal context reduces steering RMSE by 40% over the best single-frame encoder. We then train a latent Diffusion Transformer (DiT) and, through a controlled diagnosis, identify the four ingredients it needs: spatial tokens, the $x_0$ objective, residual anchoring, and sampling matched to target uncertainty. In a Stable-Diffusion-VAE encode-predict-decode pipeline we expose the central tension: distortion metrics (cosine similarity, SSIM) favor the blurry mean, masking that the diffusion model is far closer to the real frame distribution. Inception-based FID and KID reveal a clean perception-distortion frontier: diffusion attains KID 0.078 versus 0.375 for regression ($4.8\times$ better), and a deployable train-derived calibration makes this practical without test-time ground truth. The model is genuinely action-controllable (steering drives scene displacement, Spearman $\rho = 0.81$, vs $-0.18$ for regression). We trace limited single-pass motion to a shared-present anchor and engineer a compact 1.7M-parameter "jump" model that recovers full ground-truth motion magnitude ($1.02\times$ GT), where single-pass models capture less than half.

Learning grounded word meaning from natural experience requires resolving two ambiguities in infant-view recordings: when the named referent appears and where it is in a cluttered frame. In SAYCam-style data, caregiver speech is sparse and weakly synchronized with egocentric video, so single-frame contrastive pairing yields noisy positives in which the intended object is absent or entangled with distractors. We propose BabyMind, an object-first bias for child-view contrastive learning under sparse, noisy supervision. BabyMind extracts candidate object embeddings using an offline mask-based region interface, links candidates across a short utterance-centered window into lightweight object files via tracking, and aligns utterances to bags of object files with a prototype-space multiple-instance contrastive objective. Track-coherence and global-object agreement regularizers stabilize learning and transfer object-file structure into the global frame embedding used at evaluation. On SAYCam-S, BabyMind improves Labeled-S 15 forced-choice accuracy by +2.6 points over CVCL and yields consistent gains on in-vocabulary out-of-distribution benchmarks. Code is available at this https URL.

Image-based AI assistants are now deployed at production scale on e-commerce platforms, where a single uploaded image can trigger fundamentally different user intents: product search, style recommendation, visual encyclopedia, or utility tool calls, each demanding its own response format, tool invocation, and domain knowledge. Without per-intent behavioral constraints, LLM-based systems conflate these heterogeneous modes and fall short of domain quality standards, while the breadth and dynamism of the intent space render manual engineering infeasible. To address this, we present SkillChain, which closes the production feedback loop on Skill evolution, automating the lifecycle of Skills through three stages: Skill Creator for bootstrapping from task specs and trajectories, Route Optimizer for routing alignment, and Body Refiner for iterative Skill Body refinement via dual-path LLM-Judge evaluation. Deployed on a production-scale e-commerce image assistant, SkillChain substantially improves aggregate response quality, with the strongest gains on structural compliance and content quality; a one-week online A/B experiment further confirms significant gains in user engagement, content consumption, and long-term retention.

Automated testbench generation has become a critical bottleneck in large language model (LLM)-driven Register Transfer Level (RTL) workflows, where large numbers of candidate designs must be verified rapidly and reliably. Existing prompt-based approaches treat testbench generation as unconstrained code synthesis, yielding stochastic outputs with high token cost, low reproducibility, and insufficient coverage. To address this gap, we present STG, a Structured Testbench Generation framework that exploits the inherent structure of hardware designs to generate deterministic testbenches. As a direct verification tool, STG runs 720x faster than an iterative LLM-based testbench generation flow and higher rate of successful compilation, achieves higher coverage, and reduces false-pass verdicts on incorrect DUTs. STG also helps identify errors in RTL generation benchmarks by exposing faulty benchmark testbenches. As a data curation engine, it is 11x faster than LLM-based filtering on a single CPU core with 127x less energy, and the resulting distilled models provide state-of-the-art performance in our multi-benchmark evaluation. As a test-time scaling oracle, it reduces node count by 14-47\%. Our models are available at this https URL.

We describe a Camera and LiDAR fusion detector developed for the TUMTraf V2X cooperative 3D object detection track of the DriveX 2026 challenge. The detector fuses three roadside cameras with a fused infrastructure-plus-vehicle point cloud in a shared bird's-eye-view space and predicts boxes through a CenterPoint-style head with a generalized IoU regression loss and an IoU quality re-ranking head. Trained on the provided train and validation splits, the model reaches a 3D mAP of 0.85 on the public Codabench test split. While iterating on the system, we observed that 44 of the 50 test frames are also present in the released train (40) and validation (4) splits with their labels. We therefore conducted two additional studies to quantify how this overlap affects the final score: (1) a finetuning run that oversamples the 44 overlapping frames, reaching 0.89 mAP, and (2) a post-processing run that replaces predictions on those frames with the released ground truth, reaching 0.99 mAP (uploaded to our Codabench account for testing but not published on the leaderboard). All three configurations and their per-class results are reported.

JEPA-family world models use a static predictor whose weights do not adapt when test-time dynamics diverge from training. We compare two mechanisms for incorporating accumulated experience into a JEPA predictor under distribution shift: operand-side injection, where a compressed experience representation is added as a residual to the predictor's hidden state (EI-JEPA), and operator-side modulation, where the same representation generates low-rank weight deltas via LoRA applied to the predictor's weights (EPM-JEPA). On a pre-registered comparison (Moving MNIST, gravity shift), EPM-JEPA (D_shift^{n=50} = 0.7848 +/- 0.0078, three seeds) differs from EI-JEPA (0.8238) by delta = 4.74% - Outcome C: a null result - by our stated criterion, a valid outcome. As a secondary, non-pre-registered observation, EPM-JEPA improves 1.90% over a no-memory baseline (0.8000), consistently across seeds, while EI-JEPA underperforms the baseline, indicating the benefit is specific to weight-level modulation. Our primary contribution is a mechanism analysis: the D_shift^{n=50} trajectory reflects three independent dynamical processes - buffer cycling, EMA target drift, and an intrinsic LoRA settling transient of +0.021 - rather than convergence to equilibrium. These findings motivate PEM-JEPA, a physics-grounded successor addressing this dynamical-peak limitation.

Vision-language-action (VLA) policies bring natural language into closed-loop robot control, enabling robots to execute manipulation tasks directly from text instructions. The same interface gives text a recurring role in control because the prompt is reused at every replanning step, and each prompt-conditioned action changes the future observations on which the policy acts. Existing VLA attacks study adversarial prompts that elicit targeted low-level actions or make such actions persist across changing images. We identify a stronger trajectory-level failure mode: a prompt that still $\textit{appears}$ to specify the intended task but redirects the final physical outcome. We mathematically formalize this setting as $\textit{command-preserving trajectory redirection}$, a prompt-only threat model in which the attacker chooses one prompt before the episode, all policy and environment components remain fixed, and the prompt must stay close to the benign instruction while omitting target words and correction language. To find such prompts, we introduce an on-policy prompt search method that uses rollouts to discover perturbations whose closed-loop behavior tracks a target task while satisfying the command-preserving constraints. Experiments in simulation and on hardware show that near-benign prompt perturbations can redirect VLA rollouts to attacker-specified targets. These results expose a trajectory-level vulnerability in VLA instruction grounding: text that appears to preserve the intended command can still give an adversary control over the robot's final physical outcome. Project website: this https URL

Model fingerprinting, embedding user-specific identifiers (fingerprints) into generated outputs, has recently emerged as a popular solution to protect the intellectual property rights (IPR) of generative text-to-image (T2I) models and prevent unauthorized redistribution. In this work, we reveal a previously unexplored systematic vulnerability in existing generative model fingerprinting methods: they lack robustness against collusion attacks, where multiple attackers combine their models to remove or obscure the fingerprints. To address this issue, we take the first step towards a robust fingerprinting method for T2I models with anti-collusion capabilities. The proposed method encodes strings of bits, namely fingerprints, into the coefficients of a personalized normalization module (PNM) incorporated into T2I models, so that fingerprints can be reliably recovered from any generated image. To defend against collusion attacks and prevent unauthorized model redistribution, we introduce an anti-collusion mechanism based on lossless function-invariant parameter transformations. This mechanism significantly degrades the image generation quality of colluded models, making them effectively unusable. Moreover, our method allows developers to efficiently create multiple copies of fingerprinted T2I models by reparameterizing the PNM without the need for retraining. We also introduce a worst-case optimization strategy to improve robustness against model-level attacks. Our experiments demonstrate that the proposed method achieves high fidelity and robustness across multiple T2I image generation and editing tasks, with fingerprint extraction accuracy exceeding 99.5%. Compared with existing methods, our method demonstrates, for the first time, a notable proactive robustness to collusion attacks by significantly increasing the FID of colluded models.

Sharing mathematical content in online forums remains a significant friction point for students and educators: writing raw LATEX is error-prone, standalone optical character recognition tools require platform switching, and current forum software offers no integrated path from a photograph of a formula to a rendered post. We present a unified system that eliminates this friction by embedding an image to LATEX conversion pipeline directly inside a forum posting interface. A user uploads or captures an image of a mathematical expression; the system routes it through the Mathpix OCR API, detects whether the returned output is LATEX or plain text containing inline math, applies the appropriate delimiter normalisation, and renders a live preview in either LATEX or Markdown mode before the post is committed to the database. The architecture is organized in three loosely coupled layers: image processing, rendering, and storage, and supports both desktop and mobile clients. A provisional US patent application has been filed covering the core methods. We describe the full system design, each component in detail, the data schema, and the key technical innovations, and we position the work against existing standalone tools and forum platforms to demonstrate the practical gap it closes. Beyond immediate usability, we argue that a deployed platform of this kind constitutes a continuously growing, community-validated dataset of mathematical problems and step-by-step solutions, a resource that can be used to train and benchmark AI systems for accurate mathematical reasoning

Estimating cognitive load from speech has largely been studied in controlled laboratory settings, with limited understanding of its reliability in natural collaborative conversations. We investigate whether speech and interaction dynamics predict perceived cognitive load during dyadic conversations. We analyze audio from 53 dyads performing nine collaborative tasks and extract static acoustic, dynamic, and interaction features to train a two-head Gated Recurrent Unit encoder to predict cognitive load scores. Results show conversational interaction provides useful signals for predicting cognitive load related to time pressure, mental work, effort, and task performance. Temporal demand is associated with turn-taking dynamics such as overlap and speaker switch, while mental demand is linked to imbalanced participation between speakers. These findings highlight the importance of task structure and conversational interaction for modeling cognitive load in natural collaborative settings.

Grokking -- where a transformer on modular arithmetic suddenly transitions from near-chance to near-perfect validation accuracy -- is attributed to a Fourier circuit, but its timing, causal structure, and controllability remain poorly understood. We introduce the Frequency Synchronization Degree (FSD), a normalised, permutation-tested metric for Fourier circuit synchronisation requiring no prior circuit knowledge. Across nine modular addition configurations (primes p in {53, 71, 97, 113, 131}, three seeds), FSD synchronises 500-3,000 steps before grokking (mean lead +1,722 steps; all nine positive, sign-test p~0.004), and precedes a restricted-logit loss baseline (Nanda et al.'s excluded loss) in all nine cases, making it the earliest available predictor. We provide direct causal evidence that the inter-phase gap is a regularisation phenomenon: forking training at the FSD-ceiling step and varying weight decay lambda produces strictly monotone earlier grokking, with Delta_t proportional to 1/lambda. This law replicates across three primes (p in {53,97,131}; R^2=1.00 and R^2=0.99 for two clean cases), captured as Delta_t ~ C/lambda, consistent with (1/lambda)*log(||W_mem||/tau). Architecture ablations show an attention-only model groks with a strong FSD precursor; an MLP-only model never groks; a single-layer model's FSD lags, confirming the precursor is a multi-block circuit property.

Scalable robot imitation learning relies on large-scale heterogeneous data from diverse robots or body-free data, making Cartesian end-effector actions a key interface for embodiment-agnostic policy learning. However, end-effector-only abstraction leaves Cartesian policies unaware of the deployed robot body, making them brittle under robot-specific constraints such as whole-body collision avoidance. To overcome this limitation, we present EmbodiSteer, a training-free framework that steers embodiment-agnostic visuomotor policies toward zero-shot, embodiment-aware deployment. EmbodiSteer keeps policy learning in Cartesian space while efficiently lifting inference-time diffusion sampling into the target robot's joint space via forward kinematics and Jacobian-based updates. With whole-body collision-aware guidance over joint trajectories after each denoising step, the arm can be steered away from collisions while preserving learned end-effector behavior. Compared with Cartesian-only execution, EmbodiSteer reduces collision rate by 46.1% and improves task success rate by 28.5% across 9 simulated robots, and further achieves 90.0% collision rate reduction and 36.7% success rate increase on two physical robots in highly constrained scenarios. Our project page is at this https URL.

Crack detection plays an important role in infrastructure inspection and Structural Health Monitoring (SHM). However, cracks typically appear as thin, low-contrast structures and are easily affected by background noise, posing challenges for existing object detection models. This study proposes an improved YOLO-based architecture with integrated attention mechanisms, termed YOLO-AMC (YOLO with Attention Mechanisms for Crack Detection), to enhance automated crack detection performance. Based on YOLOv11, the original C2PSA module is removed, and multiple attention mechanisms, including Global Attention Mechanism (GAM), Residual Convolutional Block Attention Module (Res-CBAM), and Shuffle Attention (SA), are introduced into the multi-scale feature fusion layers of the Neck to strengthen cross-scale feature integration. Experimental results demonstrate that YOLO-AMC consistently outperforms baseline models YOLOv11n and YOLOv8n across multiple evaluation metrics. Among the evaluated attention modules, GAM achieves the best detection performance, obtaining mAP@0.5 = 0.9917 and mAP@0.5:0.95 = 0.9506 on the test dataset, which are higher than those of YOLOv11 (0.9833 / 0.9112) and YOLOv8 (0.9707 / 0.8921). Furthermore, while maintaining a computational complexity of 7.6 GFLOPs, the proposed model achieves 110.95 FPS on an NVIDIA RTX 4090 platform and approximately 5 FPS on a Raspberry Pi 5 edge device, demonstrating a favorable trade-off between accuracy and deployment efficiency. The implementation code for this study is available on GitHub at this https URL.

Long-horizon robot mobile manipulation requires continual reasoning about localization, environment changes, and task progress, all of which are challenging to infer from image observations alone. In this paper, we show that conditioning a mobile manipulation policy on a spatiotemporal feature map improves reasoning over long horizons. The map represents the environment and the articulated robot body as neural points in a shared latent space and is updated online from egocentric observations and proprioceptive state. We update the environment neural points using object-level rigid tracking and the robot neural points using forward kinematics. We use our spatiotemporal environment and robot feature (SERF) map as a state input to a vision-language-action (VLA) model by extracting map tokens from multiple reference frames and spatial scales, providing the policy with both local and global context. We demonstrate SERF on BEHAVIOR-1K, a benchmark for long-horizon mobile manipulation in household environments. Experiments show that the SERF VLA policy outperforms image-only baselines, reaches subgoals faster by following more direct trajectories, improves robustness to scene-configuration shifts, and recovers from object-drop failures.

We present OpenMedQ, a medical vision-language model pretrained on the broadest fully-open medical mix to date: 14 datasets totaling ~3.35M pretraining samples spanning pathology, radiology, microscopy, and text-only clinical QA. OpenMedQ reaches state-of-the-art BLEU-1 on PathVQA (75.9), beating Med-PaLM M variants up to 562B parameters (~80x larger), and matches the best reported VQA-MED BLEU-1 (64.5). Its vision encoder, transferred to 8 unseen medical classification benchmarks under an identical downstream recipe, obtains the highest average macro-F1 (0.757) among BiomedCLIP (0.745), PMC-CLIP (0.745), PubMedCLIP (0.746), and a from-scratch baseline (0.616). We release our code and an interactive demo is publicly available as a reproducible baseline for the community.

Long-running LLM agents accumulate interaction histories far larger than any context window, forcing a standing decision: what to encode deeply, what to forget, and what to retrieve under a fixed memory budget. Production systems answer with semantic similarity or recency -- both mis-specified for the forgetting decision, which is made at consolidation time before the future query is known. We propose a multi-factor memory value function V(m)=\sum_i w_i f_i(m) over seven interpretable factors (emotional intensity, goal relevance, value alignment, self/user relevance, task utility, reliability, and usage history) drawn from cognitive psychology, whose weights are learned from a downstream objective by a gradient-free optimiser, and whose single scalar uniformly controls encoding depth, forget risk, and retrieval rank. We make a methodological point: on LongMemEval, scoring goal relevance against the held-out evaluation question saturates gold-evidence retention at \approx 0.98 -- this measures retrieval, not forgetting. In the realistic blind regime, a learned multi-factor value retains 0.770 \pm 0.011 of gold evidence across 479 usable cases, versus 0.657 for uniform weights, 0.518 for the best single factor, and 0.368 for recency; every paired gap's 95% bootstrap CI is above zero, and a neural network over the same factors ties the linear model. The learned weights are interpretable -- reliability, emotional intensity, and self/user relevance dominate, while query-time goal similarity is correctly down-weighted for the forgetting decision. A controlled synthetic task with planted confounds confirms the learner recovers a separating weighting (1.00 retention) where uniform weighting fails (0.62). The substrate is open-source; all experiments run on a single CPU with no API calls.

Generative listwise ranking with Large Multimodal Models (LMMs) aims to capture global list context in a single forward pass, but its effectiveness degrades in long-context multimodal scenarios. We identify a recurring failure mode, parse collapse, where the autoregressive decoder produces fluent yet incomplete rankings by silently omitting candidates and terminating early. This failure stems from limited context utilization rather than simple formatting mistakes, making prompt engineering and constrained decoding insufficient. We propose PRISMR (Parameterized Representation Internalization for Semantic Multimodal Ranking), a framework that replaces transient in-context list processing with parametric structural conditioning. PRISMR uses a lightweight hypernetwork to encode multimodal candidates in parallel and generate item-specific LoRA weights, which are synthesized into an instance-specific adapter for a LMM. This paradigm enables more robust internalization of list structure while preserving the base model. We further introduce a large-scale multimodal review-ranking benchmark for evaluation. Experiments demonstrate that PRISMR substantially reduces parse collapse, improves listwise ranking performance, and transfers effectively across domains and instruction-tuned backbones.

When a user reveals task-critical information across several conversation turns, LLM accuracy drops by up to 65% despite full context availability. We show that this Lost in Conversation degradation can be substantially mitigated by training models to maintain a compact rolling memory instead of attending to a growing history. To make such training scalable, we introduce a low-cost sharding pipeline that converts single-turn QA datasets into multi-turn fragmented-information episodes, eliminating the need for hours of manual annotation. Training only on sharded GSM8K, our memory-augmented policy significantly improves multi-turn accuracy and generalises zero-shot to harder math and out-of-domain long-context QA. Moreover, memory-trained models outperform full-history baselines even when given the full history at test time, suggesting that learning to compress induces more robust incremental reasoning than full-context exposure alone.

3D point cloud models suffer significant performance degradation under distribution shifts caused by sensor noise, occlusions, and environmental changes. Test-time adaptation (TTA) has emerged as a practical paradigm for mitigating this issue during inference. Recently, leveraging multi-view augmentation has shown promise in improving 3D TTA performance. However, existing multi-view approaches are often constrained by sequential optimization that treats each view independently. This sequential optimization leads to substantial inference latency due to repetitive optimization steps, making real-time adaptation impractical. To address this, we propose Masked Multi-View Test-Time Adaptation (MAMVI), which replaces sequential optimization with a unified single-step adaptation. Specifically, MAMVI utilizes a hybrid masking strategy that combines fixed ratios for stability with Beta-distributed sampling for diversity. By aggregating losses across multiple views, MAMVI performs adaptation through a single backward pass based on multi-view consensus. Additionally, a confidence-based adaptive learning rate is used to dynamically adjust the adaptation intensity for each sample. Extensive experiments on ModelNet-40C, ShapeNet-C, and ScanObjectNN-C demonstrate that MAMVI achieves state-of-the-art accuracy on ShapeNet-C and ScanObjectNN-C. Moreover, it remains competitive on ModelNet-40C while delivering 4.9-8.9 times faster inference, making it highly suitable for real-time applications. Our code is available at this https URL

Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial computational overhead. We observe that probing partial traces at intermediate checkpoints can extract current answers without disrupting generation, revealing an evolving aggregate vote. Based on this observation, we introduce MARS, a margin-adversarial stopping rule that estimates which active traces are likely to change their answers and stops once the leader remains safe under a conservative bound on future vote movement. The rule separates two sources of uncertainty. It learns the trace-level switch probabilities that determine how much of the current margin is likely to be retained, while handling the harder question of where switching traces land through an adversarial bound calibrated from warmup traces. With true switch probabilities, MARS guarantees with high probability that the early-stopped answer matches the full-budget vote. In practice, a five-feature logistic model closely matches oracle switching behavior. Across three reasoning models and three competition-math benchmarks, MARS saves 25-47% of self-consistency tokens and 14-29% on top of DeepConf Online, a strong confidence-weighted baseline that already filters and truncates weak traces, while matching the accuracy of the corresponding full-budget baselines.

We present a modular two-agent simulation framework for evaluating conversational shopping assistant architectures. An independent buyer agent, configured with personas, missions, and patience levels, is paired with an interchangeable responder that integrates with a real e-commerce search API. Holding the buyer constant across experiments enables controlled comparison of responder designs on identical scenarios. Using 2011 conversations across 14 persona buckets, we establish four empirical findings. First, rolling-window memory outperforms intent-extraction memory on all quality metrics while being 35% faster per query. Second, illustrating rapid evidence-driven iteration, a systematic failure analysis of a responder version enables targeted fixes that reduce failure and near-failure rates by 62% across the full dataset. Third, swapping the responder LLM backbone from Gemini~2.5 to Llama~3.3~70B costs 0.16--0.45 points despite identical architecture. Finally, we document systematic philosophical disagreement between frontier LLM judges: Gemini rewards process correctness while Claude demands concrete outcomes, despite using the same evaluation prompt.

AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing objects. We argue that order is not control. Control requires a receiver-gated response law: a denominator-indexed operator mapping material state, action/drive, bath, and receiver state to response displacement, sinks, effort, and basin projection. We identify it across biological, LLM, adapter, and stochastic-operator panels. The laws are local: an intervention can be admitted, saturated, sign-changing, leaky, or overdriven depending on medium, bath, receiver state, action port, and comparator. Control is assigned when finite effort moves a target or outcome-readout class under the same denominator while damage, null/evasive, invalid format, overdrive, and unnecessary effort stay bounded. Mouse ALM, C. elegans, and zebrafish panels provide physical response-operator evidence while excluding coordinate identity and controller conclusions. LLM panels show generated-output response laws: across four material conditions, response vectors are predictable at 72.8-73.7% component-sign accuracy, rising to 84.3-84.8% on nonzero components; held-out observers predict system-effect and target/oracle families at 93.6% and 91.7% accuracy. Constitution-conditioned adapters reshape susceptibility as prepared media, and stochastic-operator panels separate measured opportunity from deployable action policies. This gives a driven-dissipative response-system account at the mesoscopic control level: drives act through prepared media, baths, and receivers, producing admitted movement, impedance, sinks, or overdrive. The evidence supports local admitted control and measurable stochastic response operators, while leaving deployable pre-generation control, hidden/logit causal sufficiency, biological-to-LLM coordinate identity, and literal thermodynamic quantities outside scope.

Political bias in large language models (LLMs) is increasingly significant, but difficult to measure reproducibly across political and linguistic contexts. We introduce Polar, a 4,026-instance multiple-choice benchmark that measures political bias through option-level likelihoods rather than prompt-based generation. Polar covers two ideological axes and eight issue categories derived from the Manifesto Project, and evaluates models in parallel across U.S. and South Korean political contexts. Across 38 LLMs, measured bias varies systematically with political context, issue category, model group, and presentation language. All models lean left-progressive on U.S. political content, but show more centered and mixed patterns on South Korean content. Translation experiments further show that presentation language alone can shift measured bias. These findings highlight the need for multilingual and cross-contextual evaluation of political bias in LLMs.

Low-Rank Adaptation (LoRA) significantly reduces compute and memory costs for finetuning Deep Learning models but is often harder to tune than dense training: when using factor-wise optimizers such as AdamW, it is sensitive to initialization choices, its optimal learning rates transfer poorly across ranks, and it often fails to beat dense baselines. We derive LoRA-Muon by applying the Muon optimizer's spectral steepest-descent rule to the low-rank setting. Along with our split weight-decay rule, our main claim is that LoRA-Muon is a good low-rank proxy for full-rank Muon and Shampoo-family optimizers. Its optimal learning rates transfer across rank, width, depth, and factor-rescaling. In our compute-matched TinyShakespeare study, a rank-$2$ proxy recovers the dense best tested learning rate, and a rank-$32$ LoRA-Muon run attains lower mean validation loss than the dense baseline in the seed-averaged sweep. We further show that the Spectron optimizer depends on arbitrary factor scaling, so it would likely be a poor fit when finetuning starts from badly imbalanced factors, and that LoRA-RITE's simplified QR-coordinate core implements the same spectral update. LoRA-Muon computes that update without QR-decomposition and avoids storing second moments, making it more accelerator-friendly and memory-efficient.

Molecular dynamics (MD) is the canonical in-silico method for atomistic molecular science, simulating molecular behavior from first-principle physics. Designing an MD pipeline for a new system requires substantial expert knowledge: running it on even one molecule is expensive, ruling out trial-and-error. We automate this expert pipeline-design process with an LLM agent. Unlike existing MD agents that orchestrate a predefined tool set, we treat pipeline design as open-ended code generation in which the agent's behavior is reshaped online by verbal reward. Specifically, we build MDForge, an LLM agent whose in-context update rule densifies the sparse reward via a multi-agent debate among physics experts. On three SAMPL host-guest binding free-energy benchmarks, MDForge automatically designs MD pipelines competitive with human experts. Deployed on a library of unseen candidate guests, its CB[7] pipeline discovers a novel binder that wet-lab competition NMR confirms is a high-affinity, picomolar CB[7] binder. Our data and code are available at this https URL.

Language model agents are increasingly effective in solving realistic tasks through multi-turn tool use. However, training reliable tool-using agents remains challenging in practice. While reinforcement learning provides an on-policy paradigm for improving agents from their own environment interactions, its effectiveness depends heavily on the training task distribution. When tasks are fixed before training, the task distribution can become increasingly mismatched with the policy's evolving capabilities, causing many rollouts to be spent on uninformative tasks. We propose SENTINEL, a failure-driven reinforcement learning framework that turns the Solver's rollout failures into targeted training tasks. SENTINEL follows a Controller--Proposer--Solver loop: the Controller analyzes failed trajectories and summarizes recurring error patterns, the Proposer generates executable tasks that stress these weaknesses, and the Solver is trained on the targeted tasks. On Tau2-Bench Retail with Qwen3-4B-Thinking-2507, SENTINEL improves Pass\^{}1 from 66.4 to 74.9 and outperforms RL on general synthetic tasks across Pass\^{}k metrics. These results demonstrate that model failures provide an effective and scalable source of targeted training signal for improving tool-using language model agents.

Retrieval-augmented generation (RAG) systems may receive evidence that is not merely noisy but mutually contradictory. This issue becomes particularly salient in multilingual settings, where retrieved Chinese and English evidence may support incompatible answer candidates. We study this problem through X-RAMDocs-ZHEN, a controlled Chinese-English benchmark derived from RAMDocs for diagnosing evidence conflict in RAG. The benchmark contains 300 examples across six balanced conditions, including monolingual support, bilingual agreement, reversed conflict directions, and conflict with optional noise. We further examine X-MADAM-RAG, an interpretable pipeline that decomposes evidence handling into per-document candidate extraction, visible-evidence repair, deterministic candidate grouping, and conflict-aware aggregation. On the original controlled benchmark with Qwen2.5-7B-Instruct, X-MADAM-RAG achieves 0.9667 strict accuracy and 0.9767 conflict-aware success, outperforming an evidence-normalized single-call baseline. However, a zero-call rule-only extractor reaches 1.0000 on the same benchmark, revealing strong template regularity. To probe this limitation, we construct a deterministic naturalized stress test that removes explicit answer templates while preserving candidate strings. On its 100-sample subset, rule-only extraction falls to 0.0000, but X-MADAM-RAG also drops to 0.3000 strict accuracy, below both naive and evidence-normalized baselines. A privileged oracle remains perfect, indicating that document-level extraction is the main bottleneck. These findings position X-RAMDocs-ZHEN and X-MADAM-RAG as diagnostic tools for controlled evidence conflict rather than as evidence of general hallucination detection or robustness to natural retrieval.