大模型推理能力

LLMs as Firmware Experts: A Runtime-Grown Tree-of-Agents Framework

LLMs作为固件专家：一种运行时增长的代理树框架

Xiangrui Zhang, Zeyu Chen, Haining Wang, Qiang Li

专题命中 代码与定理证明 ：reasoning(abstract)

AI总结 本文提出FIRMHIVE框架，利用LLMs作为固件安全分析师，通过递归代理蜂群实现更深入的固件漏洞检测，提升漏洞识别率和精度。

Comments 18 pages, 13 figures

BOOP: Write Right Code

BOOP：写出正确的代码

Vaani Goenka, Aalok Thakkar

专题命中 代码与定理证明 ：reasoning(abstract)

AI总结 BOOP通过结构化框架提升编程教育中的计算思维能力，强调正确性优先的开发方法。

Proofs of Useful Work from Arbitrary Matrix Multiplication

Ilan Komargodski, Omri Weinstein

专题命中 代码与定理证明 ：verifier(abstract)

AndroByte: LLM-Driven Privacy Analysis through Bytecode Summarization and Dynamic Dataflow Call Graph Generation

Mst Eshita Khatun, Lamine Noureddine, Zhiyong Sui, Aisha Ali-Gombe

专题命中 代码与定理证明 ：reasoning(abstract)

Comments Accepted at the Annual Computer Security Applications Conference (ACSAC) 2025

My Ontologist: Evaluating BFO-Based AI for Definition Support

Carter Benson, Alec Sculley, Austin Liebers, John Beverley

专题命中 代码与定理证明 ：reasoning(abstract)

AI4DiTraRe: Building the BFO-Compliant Chemotion Knowledge Graph

Ebrahim Norouzi, Nicole Jung, Anna M. Jacyszyn, Jörg Waitelonis, Harald Sack

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 12 pages, 7 figures. Camera-ready version. Accepted to the 5th International Workshop on Scientific Knowledge: Representation, Discovery, and Assessment; 2 November 2025 - Nara, Japan; co-located with The 24th International Semantic Web Conference, ISWC 2025. Published in CEUR proceedings Vol-4065, pages 45-56

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation

Jitesh Jain, Zhengyuan Yang, Humphrey Shi, Jianfeng Gao, Jianwei Yang

机构 * Microsoft Research, Redmond（微软研究院（红mond）） ； Meta Superintelligence Labs（Meta超智能实验室） 纠错

专题命中 代码与定理证明 ：reasoning(abstract)

Comments Project Page: https://praeclarumjj3.github.io/visper_lm/

A Systematic Study on Generating Web Vulnerability Proof-of-Concepts Using Large Language Models

Mengyao Zhao, Kaixuan Li, Lyuye Zhang, Wenjing Dang, Chenggong Ding, Sen Chen, Zheli Liu

专题命中 代码与定理证明 ：reasoning(abstract)

Any theory that admits a Wigner's Friend type multi-agent paradox is logically contextual

Nuriya Nurgalieva, V. Vilasini

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 39+16 pages. Both authors contributed equally to this work. Initial versions of some of these results were included in NN's PhD thesis (ETH Zurich, 2023). v2 includes additional citations and clarifications in the outlook section

Evolaris: A Roadmap to Self-Evolving Software Intelligence Management

Chengwei Liu, Wenbo Guo, Yuxin Zhang, Limin Wang, Sen Chen, Lei Bu, Yang Liu

专题命中 代码与定理证明 ：reasoning(abstract)

PAT-Agent: Autoformalization for Model Checking

Xinyue Zuo, Yifan Zhang, Hongshu Wang, Yufan Cai, Zhe Hou, Jing Sun, Jin Song Dong

专题命中 代码与定理证明 ：planning(abstract)

Comments Accepted in ASE 2025 (International Conference on Automated Software Engineering)

L-Mosaics and Bounded Join-Semilattices in Isabelle/HOL

Alessandro Linzi

专题命中 代码与定理证明 ：reasoning(abstract)

Hornet Node and the Hornet DSL: A Minimal, Executable Specification for Bitcoin Consensus

Toby Sharp

专题命中 代码与定理证明 ：reasoning(abstract)

Designing a Lightweight GenAI Interface for Visual Data Analysis

Ratanond Koonchanok, Alex Kale, Khairi Reda

专题命中 代码与定理证明 ：reasoning(abstract)

Requirements Development and Formalization for Reliable Code Generation: A Multi-Agent Vision

Xu Lu, Weisong Sun, Yiran Zhang, Ming Hu, Cong Tian, Zhi Jin, Yang Liu

专题命中 代码与定理证明 ：reasoning(abstract)

Street View Sociability: Interpretable Analysis of Urban Social Behavior Across 15 Cities

Kieran Elrod, Katherine Flanigan, Mario Bergés

机构 * Carnegie Mellon University（卡内基梅隆大学） 纠错

专题命中 代码与定理证明 ：planning(abstract)

What's in a Proof? Analyzing Expert Proof-Writing Processes in F* and Verus

Rijul Jain, Shraddha Barke, Gabriel Ebner, Md Rakib Hossain Misu, Shan Lu, Sarah Fakhoury

专题命中 代码与定理证明 ：verifier(abstract)

Interpreting Multi-band Galaxy Observations with Large Language Model-Based Agents

Zechang Sun, Yuan-Sen Ting, Yaobo Liang, Nan Duan, Song Huang, Zheng Cai

专题命中 代码与定理证明 ：reasoning(abstract)

Comments Accepted at the NIPS ML4PS Workshop 2024. The journal version is in preparation. Code and data will be fully made public following the journal publication. We welcome any comments and feedback

FaultLine: Automated Proof-of-Vulnerability Generation Using LLM Agents

Vikram Nitin, Baishakhi Ray, Roshanak Zilouchian Moghaddam

专题命中 代码与定理证明 ：reasoning(abstract)

Supporting Software Formal Verification with Large Language Models: An Experimental Study

Weiqi Wang, Marie Farrell, Lucas C. Cordeiro, Liping Zhao

专题命中 代码与定理证明 ：verifier(abstract)

Comments Accepted for publication in 2025 IEEE 33rd International Requirements Engineering Conference (RE)

Context-Aware CodeLLM Eviction for AI-assisted Coding

Kishanthan Thangarajah, Boyuan Chen, Shi Chang, Ahmed E. Hassan

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 12 pages, 6 figures

LLM-based Satisfiability Checking of String Requirements by Consistent Data and Checker Generation

Boqi Chen, Aren A. Babikian, Shuzhao Feng, Dániel Varró, Gunter Mussbacher

专题命中 代码与定理证明 ：reasoning(abstract)

Comments Accepted at the 33rd IEEE International Requirements Engineering 2025 conference

Quantum Agents

Eldar Sultanow, Madjid Tehrani, Siddhant Dutta, William J Buchanan, Muhammad Shahbaz Khan

专题命中 代码与定理证明 ：planning(abstract)

Comments 45 Pages, 16 figures, 3 Tables

Towards LLM-based Generation of Human-Readable Proofs in Polynomial Formal Verification

Rolf Drechsler

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 4 pages; keynote given at 7th International Symposium on Devices, Circuits and Systems (ISDCS 2025), May 27-30, 2025, IIEST Shibpur, Kolkata, India

A Bayesian Interpretation of the Internal Model Principle

Manuel Baltieri, Martin Biehl, Matteo Capucci, Nathaniel Virgo

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 14 pages, no figures

A Survey of Personalization: From RAG to Agent

Xiaopeng Li, Pengyue Jia, Derong Xu, Yi Wen, Yingyi Zhang, Wenlin Zhang, Wanyu Wang, Yichao Wang, Zhaocheng Du, Xiangyang Li, Yong Liu, Huifeng Guo, Ruiming Tang, Xiangyu Zhao

专题命中 代码与定理证明 ：planning(abstract)

Comments 18 pages, 5 figures

SpecEval: Evaluating Code Comprehension in Large Language Models via Program Specifications

Lezhi Ma, Shangqing Liu, Lei Bu, Shangru Li, Yida Wang, Yang Liu

专题命中 代码与定理证明 ：reasoning(abstract)

Safety-Critical and Distributed Nonlinear Predictive Controllers for Teams of Quadrupedal Robots

Basit Muhammad Imran, Jeeseop Kim, Taizoon Chunawala, Alexander Leonessa, Kaveh Akbari Hamed

专题命中 代码与定理证明 ：planning(abstract)

Poly-Autoregressive Prediction for Modeling Interactions

Neerja Thakkar, Tara Sadjadpour, Jathushan Rajasegaran, Shiry Ginosar, Jitendra Malik

专题命中 代码与定理证明 ：reasoning(abstract)

Comments preprint

METAMON: Finding Inconsistencies between Program Documentation and Behavior using Metamorphic LLM Queries

Hyeonseok Lee, Gabin An, Shin Yoo

专题命中 代码与定理证明 ：reasoning(abstract)

Comments 8 pages and 7 figures, accepted to LLM4Code 2025