Answer

Ask about this topic

Momentum

24 papers in the last four weeks, up 50% on the four weeks before. 0.3% of all new papers.

Jul 6Week of Sep 21
View on map

Latest papers 181

All topics
CardsList

  1. Right Answers, Wrong States: Hidden Information Failures in Multi-Agent Collaboration

    Oct 1, 2026Herun Wan, Jiaying Wu, Minnan Luo +4CollaborationMulti-Agent Reasoning

    Xi’an Jiaotong University · National University of Singapore · Yunnan University +1

  2. Beyond Final Accuracy: Auditing Communication in LLM Multi-Agent Systems

    Oct 1, 2026Shixuan Li, Wei Yang, Peiyu Zhang +3Multi-Agent CommunicationModel Auditing

    Ming Hsieh Department of Electrical and Computer Engineering University of Southern California, Los Angeles, CA 90089, USA · Thomas Lord Department of Computer Science University of Southern California, Los Angeles, CA 90089, USA

  3. Two Clocks in Diffusion MLLMs: When Answers Stabilize Before Rationales Unfold

    Oct 1, 2026Keuntae Kim, Yong Suk ChoiVisual Question Answering BenchmarksAnswer

    Department of Computer Science, Hanyang University, Seoul, Korea

  4. LLM-as-a-Judge for Low-Resource Languages: Adapting Ragas and Comparative Ranking for Romanian

    Sep 30, 2026Claudiu Creanga, Liviu P. DinuLow-Resource LanguagesRanking

    Interdisciplinary School of Doctoral Studies, University of Bucharest, Romania · HLT Research Center, University of Bucharest, Romania · Faculty of Mathematics and Computer Science, University of Bucharest, Romania

  5. When the Right Answer Is Missing: An Arithmetic-Dependent Rejection Bottleneck in Jev

    Sep 30, 2026Jike Zhong, Ming Li, Yuxiang LaiRejectionAnswer

    University of Southern California · University of Florida · Emory University

  6. Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions

    Sep 30, 2026Beiming Liu, Minjie ChenCausal InterventionDivergence

    PetroChina Southwest Oil and Gasfield Company, China

  7. Aligning Thoughts with Answers: Probability Rewards to Tame Thinking Drift

    Sep 30, 2026Pengzhan Sun, Shiu-hong Kao, Shijie Li +4Weak Visual GroundingOffline Reinforcement Learning

    National University of Singapore · A*STAR Institute of Advanced Intelligence and Computing, Singapore · South China University of Technology +2

  8. Right Answers, Costly Models: The Efficiency Gap in LLM-based Optimization Modeling

    Sep 30, 2026Zhong Li, Xin Huang, Jinhui Wan +6Optimization ModelingLarge Language Model Benchmarks

    Great Bay University · Beijing Jiaotong University · Beihang University +1

  9. Budget Boundary Effects in Test-Time Mathematical Reasoning

    Sep 30, 2026Guilin Zhang, Ziqi Tan, Wulan Guo +5Mathematical ReasoningTest Time

    Yantong AI

  10. Imagine3D-LLM: Teaching MLLMs to Imagine 3D Scenes Before Answering

    Sep 29, 2026Jaewoo Jung, Hyeonseo Yu, Honggyu An +10Spatial ReasoningMultimodal Large Language Models

    KAIST AI · ETH Zürich · Google +2

  11. Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces

    Sep 29, 2026Ratish Puduppully, Pranabendu Misra, Paarth Iyer +3Reasoning TracesChain-of-Thought Reasoning

    IT University of Copenhagen · Chennai Mathematical Institute · Indian Institute of Technology Jammu +1

  12. Locating Answer-Correctness Signals in Frozen Large Language Models

    Sep 29, 2026Yuansen Liu, Yixuan Tang, Anthony Kum Hoe TungFrozen Language ModelCorrectness

    School of Computing, National University of Singapore

  13. TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG

    Sep 29, 2026Yalun Wu, Bingzhou Wang, Boyang Wang +5Visual EvidenceMultimodal Retrieval Augmented Generation

    NExT++ Lab, National University of Singapore

  14. When Upstream Messages Override Correct Answers: A Controlled Study of Multi-Agent LLM Collaboration

    Sep 29, 2026Yaxin Gong, Gangyi Zhang, Chongming Gao +7Multi-Agent Large Language Model SystemsDownstream Reasoning

    University of Science and Technology of China · Qwen Business Unit of Alibaba · National University of Singapore

  15. Towards Mitigating Deceptive Safety Alignment in Large Reasoning Models

    Sep 28, 2026Xiangyu Zhou, Saleh Zare Zade, Rafi Ibn Sultan +2Safety AlignmentLarge Reasoning Models

    Wayne State University

  16. AnswerMap: Faithful Spatial Interpretability of VLMs from Answer Posteriors

    Sep 28, 2026Mohamed Eltahir, Fardows Adam, Duaa M. Tahir +6AnswerPosterior

    King Abdullah University of Science and Technology (KAUST), Thuwal, Saudi Arabia · Department of Computer Science, Edge Hill University, Ormskirk, England

  17. When Confidence Rises Too Early: Detecting Shortcut Reasoning via Premature Answer Commitment

    Sep 28, 2026Zhaohan Zhang, Junjie Liu, Chengzhengxu Li +6Reasoning SkillsOverconfidence

    Queen Mary University of London · Tongyi Lab, Alibaba Group · Xi’an Jiaotong University

  18. From Perception to Integration: Revisiting the Internal Dynamics of Reasoning in Vision-Language Models

    Sep 28, 2026Rong Yu Xu, Prayag Tiwari, Shaolei ZhangRecent Vision-Language ModelsVisual Reasoning

    Shenzhen College of International Education · Halmstad University, Sweden · Renmin University of China

  19. PairPref: When Should Memory Guide the Answer? A Benchmark for Contextual Preference Use

    Sep 28, 2026Mingfei Lu, Mengjia Wu, Yi ZhangPreference Alignment LearningConversational Memory

    AAII, University of Technology Sydney

  20. When Does an Image Determine the Answer? Benchmarking Visual Answerability across Charts and Scenes

    Sep 28, 2026Sungguk Cha, Mintae Kim, Youngsub Han +2AnswerChart

    LG Uplus, Seoul, South Korea

  21. Calibration, Not Answer Selection: Distilling Internal Confidence in Reasoning Models

    Sep 27, 2026Yadong Xi, Rongsheng Zhang, Tangjie Lv +2Confidence CalibrationLarge Reasoning Models

    NetEase · Amazon · Singapore University of Technology and Design

  22. Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation

    Sep 26, 2026Hantao Yu, Xiaoxue Han, Udaya Ghai +4Online-Policy DistillationInstruction

    Columbia University · Amazon Web Services

  23. Reasoning Instructions Can Break Answer Decoding in Vision--Language Models

    Sep 24, 2026Zeyan Li, Siyuan Qiu, Jianfeng XuQwen3Answer

    Shanghai Jiao Tong University

  24. Looks the Same, Answers Differently: Flip-Direction Steering for Robust Vision-Language Reasoning

    Sep 23, 2026Yeonsung Jung, Joonhyun Jeong, Hoang Pham +4Visual ReasoningSteering

    Graduate School of AI, KAIST · NAVER Cloud · Department of Computer Science and Engineering, The Ohio State University +3

  25. Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning

    Sep 23, 2026Zhixu Silvia TaoMathematical ReasoningOrder Matters

    Operations Research and Financial Engineering Princeton University Princeton, NJ 08540

  26. What Changes When Fact-Verification Scores Improve? Evidence and Answer Accounting Across Trained Verifiers and LLMs

    Sep 22, 2026Han Chen, Yingrui LiVerdictAnswer

  27. DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answering

    Sep 17, 2026Luca De Grandis, Silvia Cappelletti, William Raccagni +3Human-Annotated BenchmarkDocument

    University of Modena and Reggio Emilia, Modena, Italy · University of Modena and Reggio Emilia Modena, Italy · University of Pisa, Pisa, Italy +1

  28. Correct Now, Insufficient Later: Auditing Update Sufficiency in Context Compression

    Sep 17, 2026Guangzhe ZhangModel AuditingCorrect

    Independent AI Researcher

  29. AUDITPLAN: Commit, Then Answer for Auditable Safety Alignment

    Sep 16, 2026Sai Sri Pushpa Jampani, Kshitij Mishra, Asif EkbalSafety AlignmentModel Auditing

    Indian Institute of Technology Patna, Bihar, India

  30. Rewarding Reasoning, Not Answers: Fixing and Bounding Test-Time Reinforcement Learning on Medical QA

    Sep 15, 2026Kailong Fan, Anqi Pu, Yichen Wu +7Process Reward ModelAnswer

    1Harvard Medical School/MGH · 3Harvard University · 2Zhejiang University

  31. Vision And Text Transformer For Predicting Answerability On Visual Question Answering

    Sep 15, 2026Tung Le, Huy Tien Nguyen, Le Minh NguyenSelf-Supervised Vision TransformersTransformer Architectures

    Japan Advanced Institute of Science and Technology, Ishikawa, Japan. · Faculty of Information Technology, University of Science, Ho Chi Minh City, Vietnam · Vietnam National University, Ho Chi Minh City, Vietnam +1

  32. Beyond Safe Answers: Segment-Aware Listwise Alignment for Reasoning Safety in Large Reasoning Models

    Sep 14, 2026JungMin Yun, Junehyoung Kwon, Hayeong Ryu +3Large Reasoning ModelsReasoning Skills

    Department of Artificial Intelligence, Chung-Ang University · Graduate School of Advanced Imaging Sciences, Multimedia and Film, Chung-Ang University

  33. When Successful Knowledge Graph Edits Displace Correct Answers: Rank-Level Locality beyond Parameter Support

    Sep 14, 2026Yi-Cheng Lai, Jerry Wang, Hsin-Ling Hsu +3Multimodal Knowledge EditingKnowledge Graph Embeddings

    Institute of Information Science, Academia Sinica Taipei, Taiwan · University of Illinois Urbana-Champaign Urbana, IL, USA · National Chengchi University Taipei, Taiwan

  34. From Parameters to Answers: How LLMs Retrieve and Use Their Internal Knowledge

    Sep 12, 2026Wenkang Wei, Yuan Fang, Renhe Jiang +2Qwen3Answer

    University of Science and Technology of China Hefei, China · Singapore Management University Singapore, Singapore · The University of Tokyo Tokyo, Japan +1

  35. SearchAtlas: Analyzing Agentic Search Strategies via Evidential Query Graphs

    Sep 11, 2026Jiacheng Sang, Mengyuan Li, Sanxing Chen +3Agentic SearchQueries

    Duke University · University of Pennsylvania

  36. GANDR: Claim Auditing for Verifiable Legal Answer Generation

    Sep 9, 2026Chen Qian, Yimeng Wang, Yu Chen +2Legal Reasoning TasksCategory-Aware Atomic Claims

    William & Mary · Anytime AI

  37. Stable Answers, Unfinished Reasoning: Why Self-Consensus Is Not a Safe Early-Exit Signal

    Sep 9, 2026Yunxiang Mo, Donghao Zhao, Hejia GengSelf-ConsistencyReasoning Skills

    HKUST · University of Oxford

  38. The Era by Eon Benchmark: A Generated Enterprise Estate with Exact Ground Truth for Benchmarking LLM Agents

    Sep 9, 2026Benjamin Gruenbaum, Doron Porat, Assaf Natanzon +3Personalized Large Language Model AgentsLarge Language Model Agents

    Eon

  39. Which Medical Questions Deserve Rationales? Perturbation-Sensitive Selection for Robust QA

    Sep 9, 2026Yuexin Wu, Dayou Yu, Vasile RusMedical Visual Question AnsweringClinical Reasoning Training

    Department of Computer Science, University of Memphis

  40. FramingQA: Does the Question Shape the Answer? Measuring the Compositional Framing Effect

    Sep 7, 2026Hazel H. Kim, Andrew M. Bean, Guilherme Affonso Ferreira de Camargo +10Task FramingQuestion

    Department of Computer Science, University of Oxford · Oxford Internet Institute, University of Oxford · Thomson Reuters +7

  41. When Do Frozen VLMs Respond to Image-Free Object-Token Edits? An Answer-Key-Free Protocol and What It Reveals

    Sep 3, 2026Wonbin Son, Gyumun Choi, Junil Seo +3Frozen Vision-Language ModelsMultiple-Choice Visual Question Answering

    Changwon National University · Chung-Ang University

  42. How Correct Is Your Answer? A Semantic Correctness Framework for Open QA Evaluation

    Sep 1, 2026Elitsa Yotkova, Violeta Kastreva, Petar Velkov +4Open-Ended ResponsesAnswer

    Sofia University “St. Kliment Ohridski” · ETH Zürich · University of Zurich +1

  43. The Answer Is Not the Argument

    Aug 31, 2026Will Yeadon, Sergio Juárez, Paul Mackay +5AnswerReasoning Traces

    Department of Physics, Durham University, Durham DH1 3LE, UK · Escuela de Ingenier´ıa de Telecomunicaci´on, Department of Signal Theory and Communications, University of Vigo, Vigo E-36310, Spain · Independent Researcher

  44. Answer Probing-Guided Search for Diverse Solution Exploration of LLMs

    Aug 31, 2026Yi Fang, Que Shen, Chengpeng Li +6LLM Reasoning StrategiesReasoning Paths

    University of Science and Technology of China · Zhongguancun Academy · Alibaba Group +2

  45. Compression-Aware Abstention: Teaching LLMs to Refuse When KV-Compression Masks Remove Answer Evidence

    Aug 30, 2026Mohammadali Khodabandehlou, Bhaskar KrishnamachariLLM Inference OptimizationLarge Language Model Hallucination

    University of Southern California

  46. Candidate supply and answer selection shape the value of LLM judging in multi-agent systems

    Aug 26, 2026Jia-Hao Ji, Sijie Li, Jiabei Cheng +3Multi-Agent Large Language Model SystemsMulti-Agent Reasoning

    Department of Neurology and National Center for Neurological Diseases, Huashan Hospital, State Key Laboratory of Medical Neurobiology and Ministry of Education Frontiers Center for Brain Science, Shanghai Medical College, Fudan University, Shanghai 200040, China. · Institute of Science and Technology for Brain-Inspired Intelligence, MOE Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence, MOE Frontiers Center for Brain Science, Fudan University, Shanghai 200433, China. · Shanghai Academy of Artificial Intelligence for Science, Shanghai 200003, China. +1

  47. From Atomic Evidence to Logical Composition: Structured Compositional Reasoning over Compound Answer Options

    Aug 13, 2026Obed Junias, Maria Leonor PachecoLogicAnswer

    University of Colorado Boulder

  48. Is This Your Final Answer? Cross-Contextual Consistency as a Measure of LLM Credibility

    Aug 10, 2026Siyang Wu, Yibo Jiang, Bryon AragamLarge Language Model ReliabilityAnswer

    Data Science Institute University of Chicago Chicago, USA · Department of Computer Science University of Chicago Chicago, USA · Booth School of Business University of Chicago Chicago, USA

  49. Business Truth, not SQL Accuracy: A Rule-Gated 7B Analytics Agent Outperforms a Direct-Prompted 32B Baseline

    Aug 10, 2026Morris LeeData Science AgentsAnswer

    Independent Researcher

  50. Right Answer, Wrong Heat: Explanation-Aware Evaluation and Thermal-Grounded Feedback for MLLMs on Infrared Images

    Aug 10, 2026Yongsong Huang, Xiaofeng Liu, Tomo Miyazaki +2InfraredMultimodal Large Language Models

    Tohoku University · Yale University

  51. Muscle Memory for Agents: Compile not Merely Retrieve

    Aug 10, 2026Pouya Ghiasnezhad Omran, Soujanya Lanka, Qin Zhang +1AnswerMusculoskeletal

    Google Cloud FDE

  52. How Much Does It Cost to Answer My Question? Benchmarking Cloud VLM-based VQA Systems

    Aug 8, 2026Henri Vanhuynegem, Weitao Xu, Yiran Shen +1Recent Vision-Language ModelsQwen3

    Department of Software Technology, Delft University of Technology, Delft, The Netherlands · Department of Computer Science, City University of Hong Kong, Hong Kong SAR, China · School of Software, Shandong University, Jinan, China +1

  53. From token probabilities to calibrated confidence: An empirical study of mathematical question answering

    Aug 8, 2026Avery Ma, Lorne Schell, Vin Bhaskara +1Confidence EstimationMath Problems

    RBC Borealis

  54. DAEP: Difficulty-Aware Evidence Planning for Medical Video Corpus Temporal Answer Grounding

    Aug 7, 2026Tianjian He, Yujie Liu, Zhiping Huang +1Video Temporal GroundingTemporal Grounding

    TikTok, ByteDance, China · Beijing Institute of Graphic Communication, Beijing, China · Lingnan University, Hong Kong, China

  55. Agreement Before Diversity: Verification-First Complementarity for Heterogeneous Language-Model Coordination

    Aug 5, 2026Ruitong Li, Binjie Guo, Aisheng Mo +3DiversityAgreement

    1The University of Hong Kong · Zhejiang University · 3Independent Researcher

  56. Detecting Hallucinations and Recovering Verified Answers in Arabic Islamic Question Answering

    Aug 4, 2026Khaled ZianiCitation Hallucination DetectionHallucination Detection

    Independent Researcher, Paris, France

  57. When Many Answers Are Valid, Voting Fails: Symbolic Verification for Best-of-K Causal Reasoning in LLMs

    Aug 4, 2026Omatharv Bharat Vaidya, Connor Thomas Jerzak, Zayne Rea Sprague +2Causal ReasoningReasoning Traces

    The University of Texas at Austin · New York University

  58. Shorter Reasoning, Earlier Answers? An Evaluation of Reasoning Interfaces

    Aug 4, 2026Francesca Carlon, Vincent Ginis, Andres AlgabaReasoning TracesMmlu-Pro

    Data Analytics Lab, Vrije Universiteit Brussel, Pleinlaan 5, 1050 Brussels, Belgium · imec-SMIT, Vrije Universiteit Brussel, Pleinlaan 9, 1050 Brussels, Belgium · School of Engineering and Applied Sciences, Harvard University, Cambridge, Massachusetts 02138, USA

  59. Reachability Is Not Realization: Tracing the Sources of LLM Benchmark Gains

    Aug 4, 2026Yanchao Li, Wanhao Liu, Jiaqing Xie +4Reasoning BenchmarkPossibilities

    Nanjing University · Shanghai Artificial Intelligence Laboratory · North University of China

  60. Conformity Mitigations in Large Language Models Lie on a Single Resistance-Receptivity Frontier

    Aug 3, 2026Zafar Hussain, Kristoffer NielboMmlu-ProConformity

    Aarhus University