mlsanityData to 14 Oct 2026

BaRe-Mem: Bayesian Reliability Memory for Robust and Adaptive Agent Consultation

arXiv 2609.35551 ↗First posted 28 Sep 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

In multi-agent systems, reliable consultation is challenging because advisor capabilities vary across tasks, and misleading information can make consultation worse than autonomous reasoning. We introduce BaRe-Mem, an online Bayesian reliability memory for multi-agent consultation. It estimates advisor reliability based on the central model's internal belief representations and updates these estimates from historical interactions. These estimates modulate the influence of advisor responses and guide the choice between consultation and autonomous reasoning. Across nine benchmarks and six central models, BaRe-Mem is more robust to misleading advisor information than debate and majority voting. On the more challenging tasks, it remains above autonomous reasoning across all tested misleading levels. Moreover, we extend the BaRe-Mem mechanism to worker allocation in agent teams. On the MuSiQue benchmark, BaRe-Mem improves task completion over routing by historical success counts and identifies capable workers earlier.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 56 of its 61 references that are in the map. First posted on arXiv 28 Sep 2026.

Builds on

56 of 61 references.

References · 56

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2020Measuring Massive Multitask Language Understandingcited by 7,963
  4. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  5. 2016SQuAD: 100,000+ Questions for Machine Comprehension of Textcited by 4,148
  6. 2019PIQA: Reasoning about Physical Commonsense in Natural Languagecited by 2,883
  7. 2018Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answeringcited by 2,164
  8. 2023AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversationcited by 1,988
  9. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  10. 2022Challenging BIG-Bench Tasks and Whether Chain-of-Thought Can Solve Themcited by 1,807
  11. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  12. 2019SuperGLUE: A Stickier Benchmark for General-Purpose Language Understanding Systemscited by 1,729
38 more
  1. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  2. 2023HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Facecited by 1,190
  3. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  4. 2021MuSiQue: Multihop Questions via Single-hop Question Compositioncited by 916
  5. 2021Measuring Coding Challenge Competence With APPScited by 902
  6. 2023ExpeL: LLM Agents Are Experiential Learnerscited by 876
  7. 2025Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memorycited by 779
  8. 2024Large Language Model based Multi-Agents: A Survey of Progress and Challengescited by 769
  9. 2017Crowdsourcing Multiple Choice Science Questionscited by 765
  10. 2024Phi-4 Technical Reportcited by 711
  11. 2023LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusioncited by 564
  12. 2023MemoryBank: Enhancing Large Language Models with Long-Term Memorycited by 556
  13. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  14. 2025LLMs Get Lost In Multi-Turn Conversationcited by 429
  15. 2024Parallelizing Linear Transformers with the Delta Rule over Sequence Lengthcited by 396
  16. 2024Titans: Learning to Memorize at Test Timecited by 328
  17. 2022Memorizing Transformerscited by 226
  18. 2025Why Language Models Hallucinatecited by 220
  19. 2025Kimi Linear: An Expressive, Efficient Attention Architecturecited by 196
  20. 2023RestGPT: Connecting Large Language Models with Real-World RESTful APIscited by 135
  21. 2025G-Memory: Tracing Hierarchical Memory for Multi-Agent Systemscited by 122
  22. 2023Should we be going MAD? A Look at Multi-Agent Debate Strategies for LLMscited by 114
  23. 2025MemGen: Weaving Generative Latent Memory for Self-Evolving Agentscited by 109
  24. 2024MEMORYLLM: Towards Self-Updatable Large Language Modelscited by 93
  25. 2023Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMscited by 91
  26. 2025M+: Extending MemoryLLM with Scalable Long-Term Memorycited by 54
  27. 2025Do as We Do, Not as You Think: the Conformity of Large Language Modelscited by 53
  28. 2025Stop Overvaluing Multi-Agent Debate -- We Must Rethink Evaluation and Embrace Model Heterogeneitycited by 44
  29. 2026Doc-to-LoRA: Learning to Instantly Internalize Contextscited by 43
  30. 2024With Greater Text Comes Greater Necessity: Inference-Time Training Helps Long Text Generationcited by 37
  31. 2024Conformity in Large Language Modelscited by 34
  32. 2025Free-MAD: Consensus-Free Multi-Agent Debatecited by 29
  33. 2025Debate Only When Necessary: Adaptive Multiagent Collaboration for Efficient LLM Reasoningcited by 27
  34. 2024CrAM: Credibility-Aware Attention Modification in LLMs for Combating Misinformation in RAGcited by 22
  35. 2025MLP Memory: A Retriever-Pretrained Memory for Large Language Modelscited by 20
  36. 2025Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Modelscited by 16
  37. 2025LLMs Can't Handle Peer Pressure: Crumbling under Multi-Agent Social Interactionscited by 16
  38. 2026δ-mem: Efficient Online Memory for Large Language Modelscited by 13

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.