mlsanityData to 14 Oct 2026

Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory

arXiv 2610.19474 ↗First posted 14 Oct 2026cs.AIcited by 0

Not on the map. Why?

Abstract (arXiv)

Questions about an agent's history often require aggregating events, which retrieval alone does not resolve. We combine source-preserving evidence access with executable aggregation. Trajectory Memory (TM) retains the original trajectory and constructs a source-addressable reading view at question time. TallyMem augments it with a reusable event ledger, model-generated event specifications and deterministic execution. With a commit-specific adaptation on 776 questions from 99 held-out MINTEval repositories, TallyMem raises Qwen3-32B exact match from 35.2% to 49.0%, a 13.8-point gain over TM; gains span 12.8-13.9 points across three readers. A controlled probe with event sets parsed independently from raw logs shows an 11.0-point gain, from 82.8% to 93.8%, without routing. On full AMA-Bench, the routed system yields a smaller 1.3-point gain, from 69.8% to 71.1%. These results support executable aggregation on tasks that require combining events, with benefits dependent on the task and event specification, the largest residual system-error category in our diagnostic analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 31 references that are in the map. First posted on arXiv 14 Oct 2026.

Builds on

27 of 31 references.

References · 27

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  2. 2025Qwen3 Technical Reportcited by 8,820
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  5. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,389
  6. 2024RULER: What's the Real Context Size of Your Long-Context Language Models?cited by 1,346
  7. 2025A-MEM: Agentic Memory for LLM Agentscited by 1,063
  8. 2024OpenHands: An Open Platform for AI Software Developers as Generalist Agentscited by 1,002
  9. 2023Large Language Models Can Be Easily Distracted by Irrelevant Contextcited by 841
  10. 2024LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memorycited by 707
  11. 2024Executable Code Actions Elicit Better LLM Agentscited by 564
  12. 2024Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexitycited by 451
15 more
  1. 2019Confident Learning: Estimating Uncertainty in Dataset Labelscited by 413
  2. 2023Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoningcited by 391
  3. 2022Binding Language Models in Symbolic Languagescited by 228
  4. 2023Universal Self-Consistency for Large Language Model Generationcited by 203
  5. 2023ChatDB: Augmenting LLMs with Databases as Their Symbolic Memorycited by 140
  6. 2023Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakescited by 111
  7. 2026MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Taskscited by 84
  8. 2026AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applicationscited by 53
  9. 2025Oolong: Evaluating Long Context Reasoning and Aggregation Capabilitiescited by 40
  10. 2026MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Searchcited by 5
  11. 2026MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systemscited by 5
  12. 2026MemGym: a Long-Horizon Memory Environment for LLM Agentscited by 5
  13. 2026Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQLcited by 4
  14. 2026Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Lengthcited by 2
  15. 2026Language models fail at extended rule followingcited by 1

Built on by

Not cited yet.