Ax Xiaojie Xu, Zongyuan Li, Chang Lu, Runnan Qi, Yanan Ni, Lumin Jiang, Xiangbei Liu, Xuebo Zhang, Yongchun Fang, Kuihua Huang, Xian Guo, Zhanghua Wu, Zhenya Li 29d ago

Reflection of Episodes: Learning to Play Game from Expert and Self Experiences

Framework combining LLM self-reflection with expert and self-experience for StarCraft II gameplay. Addresses complex environment learning.

Ax Yukun Huang, Sanxing Chen, Jian Pei, Manzil Zaheer, Bhuwan Dhingra 29d ago

Cite Pretrain: Retrieval-Free Knowledge Attribution for Large Language Models

Method for LLMs to generate reliable citations without external retrievers by leveraging pretraining knowledge. Improves inference efficiency.

Ax Michael Katz, Harsha Kokel, Sarath Sreedharan 29d ago

Seemingly Simple Planning Problems are Computationally Challenging: The Countdown Game

Benchmark for evaluating long-term planning capabilities of LLMs and AI agents. Addresses gap in existing planning benchmarks.

Ax Kei-Sing Ng 29d ago

Similarity Field Theory: A Mathematical Framework for Intelligence

Mathematical framework formalizing similarity relations as structural basis for dynamic systems. Theoretical foundational work.

Ax Lianhao Zhou, Hongyi Ling, Cong Fu, Yepeng Huang, Michael Sun, Wendi Yu, Xiaoxuan Wang, Xiner Li, Xingyu Su, Junkai Zhang, Xiusi Chen, Chenxing Liang, Xiaofeng Qian, Heng Ji, Wei Wang, Marinka Zitnik, Shuiwang Ji 29d ago

Autonomous Agents for Scientific Discovery: Orchestrating Scientists, Language, Code, and Physics

Survey of autonomous LLM agents for scientific discovery, orchestrating human scientists, code, and physics simulations.

Ax Anshuman Chhabra, Shrestha Datta, Shahriar Kabir Nahin, Prasant Mohapatra 29d ago

Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

Survey of security threats, defenses, and evaluation methods for agentic AI systems with tool use, planning, and autonomous execution.

Ax Chun Chet Ng, Jia Yu Lim, Wei Zeng Low 29d ago

PRISM: Prompt-Refined In-Context System Modelling for Financial Retrieval

PRISM: Training-free framework combining prompt engineering and multi-agent coordination for financial document retrieval with LLMs.

Ax Alexander Zadorojniy, Segev Wasserkrug, Eitan Farchi 29d ago

An Agent-Based Framework for the Automatic Validation of Mathematical Optimization Models

Agent-based framework for automatic validation of mathematical optimization models generated by LLMs from natural language descriptions.

Ax Leijie Wang, Otilia Stretcu, Wei Qiao, Thomas Denby, Krishnamurthy Viswanathan, Enming Luo, Chun-Ta Lu, Tushar Dogra, Ranjay Krishna, Ariel Fuxman 29d ago

Agile Deliberation: Concept Deliberation for Subjective Visual Classification

Research on iterative concept refinement for vision classifiers through human-in-the-loop deliberation for subjective visual tasks.

Ax Haoyu Dong, Pengkun Zhang, Yan Gao, Xuanyu Dong, Yilin Cheng, Mingzhe Lu, Zikun Zhu, Adina Yakefu, Shuxin Zheng 29d ago

Finch: Benchmarking Finance & Accounting across Spreadsheet-Centric Enterprise Workflows

Finch: benchmark for evaluating agents on enterprise finance workflows including data entry, retrieval, calculation, and reporting using Enron dataset.

Ax Rahul Baxi 29d ago

The Drill-Down and Fabricate Test (DDFT): A Protocol for Measuring Epistemic Robustness in Language Models

DDFT protocol for measuring epistemic robustness in LMs under degraded information and adversarial stress beyond static benchmarks.

Ax Rongxin Chen, Tianyu Wu, Bingbing Xu, Jiatang Luo, Xiucheng Xu, Huawei Shen 29d ago

HAG: Hierarchical Demographic Tree-based Agent Generation for Topic-Adaptive Simulation

HAG framework for topic-adaptive agent generation in agent-based modeling balancing macro-level distributions with micro-level rationality.

Ax Binxu Wang, Jingxuan Fan, Xu Pan 29d ago

Circuit Mechanisms for Spatial Relation Generation in Diffusion Transformers

Mechanistic interpretability study of how Diffusion Transformers generate correct spatial relations between objects in text-to-image generation.

Ax Mayank Sharma, Roy Pea, Hari Subramonyam 29d ago

ConvoLearn: A Dataset for Fine-Tuning Dialogic AI Tutors

ConvoLearn dataset of 2,134 tutor-student dialogues for fine-tuning LLMs on dialogic tutoring principles in science education.

Ax Jon Chun, Katherine Elkins 29d ago

The Paradox of Robustness: Decoupling Rule-Based Logic from Affective Noise in High-Stakes Decision-Making

Study showing LLMs exhibit robustness to emotional framing in rule-bound decision-making despite known brittleness to prompt perturbations.

Ax Shichao Ma, Zhiyuan Ma, Ming Yang, Xiaofan Li, Xing Wu, Jintao Du, Yu Cheng, Weiqiang Wang, Qiliang Liu, Zhengyang Zhou, Yang Wang 29d ago

TSPO: Breaking the Double Homogenization Dilemma in Multi-turn Search Policy Optimization

TSPO: RL framework for multi-turn search-augmented LLM reasoning addressing process and reward homogenization in tool-integrated tasks.

Ax Wei Dai, Haoyu Wang, Honghao Chang, Lijun He, Fan Li, Jian Sun, Haixia Bi 29d ago

Enhancing Foundation VLM Robustness to Missing Modality: Scalable Diffusion for Bi-directional Feature Restoration

Method for improving Vision Language Model robustness when modalities are missing using scalable diffusion-based feature restoration.

Ax Ivaxi Sheth, Zhijing Jin, Bryan Wilder, Dominik Janzing, Mario Fritz 29d ago

IV Co-Scientist: Multi-Agent LLM Framework for Causal Instrumental Variable Discovery

Multi-agent LLM framework for discovering instrumental variables in causal inference through interdisciplinary knowledge synthesis.

Ax Mistral-AI, :, Alexander H. Liu, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Jean-Malo Delignon, Khyathi Raghavi Chandu, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Sandeep Subramanian, Soham Ghosh, Srijan Mishra, Abhinav Rastogi, Adrien Sad\'e, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Am\'elie H\'eliou, Amos You, Andrew Bai, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Avi Sooriyarachchi, Baptiste Bout, Baptiste Rozi\`ere, Baudouin De Monicault, Benjamin Tibi, Charlotte Cronj\"ager, Cl\'emence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elizaveta Demyanenko, Elliot Chane-Sane, Enguerrand Paquin, Etienne Goffinet, Fabien Niel, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Ga\"etan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Kunsch, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hope McGovern, Hugo Thimonier, Indraneel Mukherjee, Irene Zhang, Jaeyoung Kim, Jan Ludziejewski, Jason Rute, Joachim Studnia, John Harvill, Jonas Amar, Jos\'ephine Delas, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kilian Tep, Kush Jain, Laurence Aitchison, Laurent Fainsin, L\'eonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Manan Sharma, Margaret Jennings, Marie Pellat, Mark Prins, Martin Alexandre, Mathieu Poir\'ee, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mert Unsal, Mia Chiquier, Minh-Quang Pham, Nathan Grinsztajn, Neha Gupta, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philippe Pinel, Philom\`ene Chagniot, Pierre Stock, Piotr Mi{\l}o\'s, Prateek Gupta, Pravesh Agrawal, Quentin Torroba, Ram Ramrakhya, Rishi Shah, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Humeau, Sean Cha, Shashwat Verma, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Sumukh Aithal, Szymon Antoniak, Teven Le Scao, Th\'eo Cachet, Theo Simon Sorg, Thibaut Lavril, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Edwards, Tyler Wang, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Van Phung, Vedant Nanda, Victor Jouault, Vincent Maladi\`ere, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen-Ding Li, William Havard, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yannic Neuhaus, Yassine El Ouahidi, Yassir Bendou, Yihan Wang, Yimu Pan, Zaccharie Ramzi, Zhenlin Xu 29d ago

Voxtral Realtime

Voxtral Realtime: natively streaming ASR model achieving sub-second latency with end-to-end training for audio-text alignment.

Ax Bowen Liu, Zhi Wu, Runquan Xie, Zhanhui Kang, Jia Li 29d ago

Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning

SSLogic: agentic meta-synthesis framework where LLM agents iteratively create and refine generator-validator pairs for logic reasoning tasks.

Ax Yue Liu, Yingwei Ma, Yibo Miao, Yanhao Li, Yuchong Xie, Xinlong Yang, Zhiyuan Hu, Flood Sung, Jiaheng Zhang, Bryan Hooi 29d ago

KLong: Training LLM Agent for Extremely Long-horizon Tasks

KLong: open-source LLM agent trained for extremely long-horizon tasks using trajectory-splitting SFT and progressive RL with Research-Factory pipeline.

Ax Christopher Cruz 29d ago

AI Runtime Infrastructure

AI Runtime Infrastructure layer that observes and optimizes agent execution for task success, latency, token efficiency, and safety.

Ax Yukun Huang, Leonardo F. R. Ribeiro, Momchil Hardalov, Bhuwan Dhingra, Markus Dreyer, Venkatesh Saligrama 29d ago

DeepFact: Co-Evolving Benchmarks and Agents for Deep Research Factuality

DeepFact benchmark and co-evolving agent system for testing factuality of search-augmented LLM-generated research reports.

Ax Cong Cao, Jingyao Zhang, Kun Tong 29d ago

A Hierarchical Error-Corrective Graph Framework for Autonomous Agents with LLM-Based Action Generation

HECG framework for autonomous agents using LLMs with multi-dimensional error correction and strategy transfer across tasks.

Ax Hajime Shimao, Warut Khern-am-nuai, Sung Joo Kim 29d ago

Collective AI can amplify tiny perturbations into divergent decisions

Study showing that deliberation between multiple LLMs can amplify tiny perturbations into divergent decisions, challenging robustness assumptions.

Ax Haoyu He, Yu Duan, Wenzhen Liu, Hanyuan Hang, Boyu Qin, Qiantu Tuo, Xiaoke Yang, Rui Li 29d ago

A Self-Evolving Defect Detection Framework for Industrial Photovoltaic Systems

Machine learning framework for automating defect detection in photovoltaic systems using electroluminescence imaging.

Ax Houston Haynes 29d ago

Adaptive Domain Models: Bayesian Evolution, Warm Rotation, and Principled Training for Geometric and Neuromorphic AI

Proposes alternative training architecture for geometric and neuromorphic AI using non-standard arithmetic to reduce memory overhead.

Ax Huansheng Ning, Jianguo Ding 29d ago

An Onto-Relational-Sophic Framework for Governing Synthetic Minds

Conceptual framework for AI governance addressing regulatory gaps between task-specific systems and foundation models.

Ax Mistral-AI, :, Alexander H. Liu, Alexis Tacnet, Andy Ehrenberg, Andy Lo, Chen-Yo Sun, Guillaume Lample, Henry Lagarde, Jean-Malo Delignon, Jaeyoung Kim, John Harvill, Khyathi Raghavi Chandu, Lorenzo Signoretti, Margaret Jennings, Patrick von Platen, Pavankumar Reddy Muddireddy, Rohin Arora, Sanchit Gandhi, Samuel Humeau, Soham Ghosh, Srijan Mishra, Van Phung, Abdelaziz Bounhar, Abhinav Rastogi, Adrien Sad\'e, Alan Jeffares, Albert Jiang, Alexandre Cahill, Alexandre Gavaudan, Alexandre Sablayrolles, Am\'elie H\'eliou, Amos You, Andrew Bai, Andrew Zhao, Angele Lenglemetz, Anmol Agarwal, Anton Eliseev, Antonia Calvi, Arjun Majumdar, Arthur Fournier, Artjom Joosen, Avi Sooriyarachchi, Aysenur Karaduman Utkur, Baptiste Bout, Baptiste Rozi\`ere, Baudouin De Monicault, Benjamin Tibi, Bowen Yang, Charlotte Cronj\"ager, Cl\'emence Lanfranchi, Connor Chen, Corentin Barreau, Corentin Sautier, Cyprien Courtot, Darius Dabert, Diego de las Casas, Elizaveta Demyanenko, Elliot Chane-Sane, Emmanuel Gottlob, Enguerrand Paquin, Etienne Goffinet, Fabien Niel, Faruk Ahmed, Federico Baldassarre, Gabrielle Berrada, Ga\"etan Ecrepont, Gauthier Guinet, Genevieve Hayes, Georgii Novikov, Giada Pistilli, Guillaume Kunsch, Guillaume Martin, Guillaume Raille, Gunjan Dhanuka, Gunshi Gupta, Han Zhou, Harshil Shah, Hope McGovern, Hugo Thimonier, Indraneel Mukherjee, Irene Zhang, Jacques Sun, Jan Ludziejewski, Jason Rute, J\'er\'emie Dentan, Joachim Studnia, Jonas Amar, Jos\'ephine Delas, Josselin Somerville Roberts, Julien Tauran, Karmesh Yadav, Kartik Khandelwal, Kilian Tep, Kush Jain, Laurence Aitchison, Laurent Fainsin, L\'eonard Blier, Lingxiao Zhao, Louis Martin, Lucile Saulnier, Luyu Gao, Maarten Buyl, Manan Sharma, Marie Pellat, Mark Prins, Martin Alexandre, Mathieu Poir\'ee, Mathieu Schmitt, Mathilde Guillaumin, Matthieu Dinot, Matthieu Futeral, Maxime Darrin, Maximilian Augustin, Mert Unsal, Mia Chiquier, Mikhail Biriuchinskii, Minh-Quang Pham, Mircea Lica, Morgane Rivi\`ere, Nathan Grinsztajn, Neha Gupta, Olivier Bousquet, Olivier Duchenne, Patricia Wang, Paul Jacob, Paul Wambergue, Paula Kurylowicz, Philippe Pinel, Philom\`ene Chagniot, Pierre Stock, Piotr Mi{\l}o\'s, Prateek Gupta, Pravesh Agrawal, Quentin Torroba, Ram Ramrakhya, Randall Isenhour, Rishi Shah, Romain Sauvestre, Roman Soletskyi, Rosalie Millner, Rupert Menneer, Sagar Vaze, Samuel Barry, Samuel Belkadi, Sandeep Subramanian, Sean Cha, Shashwat Verma, Siddhant Waghjale, Siddharth Gandhi, Simon Lepage, Sumukh Aithal, Szymon Antoniak, Tarun Kumar Vangani, Teven Le Scao, Th\'eo Cachet, Theo Simon Sorg, Thibaut Lavril, Thomas Chabal, Thomas Foubert, Thomas Robert, Thomas Wang, Tim Lawson, Tom Bewley, Tom Edwards, Tyler Wang, Umar Jamil, Umberto Tomasini, Valeriia Nemychnikova, Vedant Nanda, Victor Jouault, Vincent Maladi\`ere, Vincent Pfister, Virgile Richard, Vladislav Bataev, Wassim Bouaziz, Wen-Ding Li, William Havard, William Marshall, Xinghui Li, Xingran Guo, Xinyu Yang, Yannic Neuhaus, Yassine El Ouahidi, Yassir Bendou, Yihan Wang, Yimu Pan, Zaccharie Ramzi, Zhenlin Xu 29d ago

Voxtral TTS

Voxtral TTS expressive multilingual text-to-speech model generating natural speech from minimal reference audio.

Ax Dan Oprisa, Peter Toth 29d ago

Metriplector: From Field Theory to Neural Architecture

Metriplector neural architecture primitive based on field theory where input configures abstract physical systems.

Ax Bowen Wei, Yunbei Zhang, Jinhao Pan, Kai Mei, Xiao Wang, Jihun Hamm, Ziwei Zhu, Yingqiang Ge 29d ago

ClawSafety: "Safe" LLMs, Unsafe Agents

ClawSafety exposes security vulnerabilities in local LLM agent frameworks where prompt injection enables privilege escalation.

Ax Prince Zizhuang Wang, Shuli Jiang 29d ago

AgentSocialBench: Evaluating Privacy Risks in Human-Centered Agentic Social Networks

AgentSocialBench evaluates privacy risks in collaborative multi-agent social networks with persistent LLM agents.

Ax Chao Li, Yuru Wang, Chunyi Zhao 29d ago

Domain-constrained knowledge representation: A modal framework

Modal framework for knowledge representation handling domain-specific concept meaning shifts in knowledge graphs.

Ax Xue Liu, Xin Ma, Yuxin Ma, Yongchang Peng, Duo Wang, Zhoufutu Wen, Ge Zhang, Kaiyuan Zhang, Xinyu Chen, Tianci He, Jiani Hou, Liang Hu, Ziyun Huang, Yongzhe Hui, Jianpeng Jiao, Chennan Ju, Yingru Kong, Yiran Li, Mengyun Liu, Luyao Ma, Fei Ni, Yiqing Ni, Yueyan Qiu, Yanle Ren, Zilin Shi, Zaiyuan Wang, Wenjie Yue, Shiyu Zhang, Xinyi Zhang, Kaiwen Zhao, Zhenwei Zhu, Shanshan Wu, Qi Zhao, Wenhao Huang 29d ago

Xpertbench: Expert Level Tasks with Rubrics-Based Evaluation

XpertBench evaluates LLM performance on expert-level open-ended tasks with rubrics-based assessment.

Ax Farzane Aminmansour, Taher Jafferjee, Ehsan Imani, Erin Talvitie, Micheal Bowling, Martha White 29d ago

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models

Addresses value hallucination in Dyna reinforcement learning agents through multistep predecessor models.

Ax Sibo Wang, Xiangkui Cao, Jie Zhang, Zheng Yuan, Shiguang Shan, Xilin Chen, Wen Gao 29d ago

VLBiasBench: A Comprehensive Benchmark for Evaluating Bias in Large Vision-Language Model

VLBiasBench evaluates biases in large vision-language models across diverse domains and question formats.

Ax D. Denipitiyage, B. Silva, K. Gunathilaka, S. Seneviratne, A. Mahanti, A. Seneviratne, S. Chawla 29d ago

Detecting and Characterising Mobile App Metamorphosis in Google Play Store

Study of app metamorphosis phenomenon where mobile apps undergo significant market repositioning.

Ax Lionel Z. Wang, Ka Chung Ng, Yiming Ma, Wenqi Fan 29d ago

MegaFake: A Theory-Driven Dataset of Fake News Generated by Large Language Models

MegaFake dataset of LLM-generated fake news for understanding mechanisms behind AI-generated misinformation.

Ax Lechen Zhang, Tolga Ergen, Lajanugen Logeswaran, Moontae Lee, David Jurgens 29d ago

SPRIG: Improving Large Language Model Performance by System Prompt Optimization

SPRIG optimizes system prompts for LLMs using genetic algorithms to improve general task performance.

Ax Qintong Zhang, Bin Wang, Victor Shea-Jay Huang, Junyuan Zhang, Zhengren Wang, Hao Liang, Conghui He, Wentao Zhang 29d ago

Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction

Comprehensive survey of document parsing techniques for extracting structured information from unstructured documents.

Ax Zhouxing Shi, Haoyu Li, Cho-Jui Hsieh, Huan Zhang 29d ago

Certified Training with Branch-and-Bound for Lyapunov-stable Neural Control

Certified Training with Branch-and-Bound for learning verifiably stable neural control systems.

Ax Feijie Wu, Zitao Li, Fei Wei, Yaliang Li, Bolin Ding, Jing Gao 29d ago

Talk to Right Specialists: Iterative Routing in Multi-agent Systems for Question Answering

RIRS framework for multi-agent RAG systems to route complex questions across distributed knowledge bases.

Ax Boran Zhang, Muhan Xu, Zhijun Pan 29d ago

Human-AI Collaborative Game Testing with Vision Language Models

Human-AI collaboration for game testing using vision language models to enhance manual testing efficiency.

Ax Aytijhya Saha, Aaditya Ramdas 29d ago

Post-detection inference for sequential changepoint localization

Framework for statistical inference on detected changepoints in sequential analysis with confidence sets.

Ax Danial Abshari, Meera Sridhar 29d ago

Cyber-Physical Systems Security: A Comprehensive Review of Anomaly Detection Techniques

Review of anomaly detection techniques for cyber-physical systems security in critical infrastructure.

Ax Messi H. J. Lee, Calvin K. Lai 29d ago

Implicit Bias-Like Patterns in Reasoning Models

Reasoning Model Implicit Association Test studies implicit bias-like patterns in LLMs that use step-by-step reasoning.

Ax Dipesh Tamboli, Souradip Chakraborty, Aditya Malusare, Biplab Banerjee, Amrit Singh Bedi, Vaneet Aggarwal 29d ago

BalancedDPO: Adaptive Multi-Metric Alignment

BalancedDPO method aligns diffusion models with multiple conflicting evaluation metrics for text-to-image generation.

Ax Yunqi Shi, Chengrui Gao, Wanqi Ren, Peng Xie, Siyuan Xu, Ke Xue, Mingxuan Yuan, Chao Qian, Zhi-Hua Zhou 29d ago

Open3DBench: Open-Source Benchmark for 3D-IC Backend Implementation and PPA Evaluation

Open-source benchmark for 3D chip design using OpenROAD framework, evaluates power, performance, area, and thermal metrics.

Ax Felipe Azua, Leopoldo Bertossi 29d ago

Causality-Based Scores Alignment in Explainable Data Management

Investigates alignment of causal attribution scores (Shapley, Banzhaf, Causal Responsibility) for database tuple relevance in data management.

Ax Tongrui Su, Qingbin Li, Shengyu Zhu, Wei Chen, Xueqi Cheng 29d ago

RaPA: Enhancing Transferable Targeted Attacks via Random Parameter Pruning

RaPA improves transferable targeted adversarial attacks by identifying and pruning redundant surrogate model parameters.