# Beyond Retrieval: Evidence Access and Event Aggregation in Agent Memory

arXiv: https://arxiv.org/abs/2610.19474 · HTML: https://mlsanity.com/paper/2610.19474/

## 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 (most cited first, 27 of 27)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [RULER: What's the Real Context Size of Your Long-Context Language Models?](https://mlsanity.com/paper/2404.06654/) (2024)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [Large Language Models Can Be Easily Distracted by Irrelevant Context](https://mlsanity.com/paper/2302.00093/) (2023)
- [LongMemEval: Benchmarking Chat Assistants on Long-Term Interactive Memory](https://mlsanity.com/paper/2410.10813/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Adaptive-RAG: Learning to Adapt Retrieval-Augmented Large Language Models through Question Complexity](https://mlsanity.com/paper/2403.14403/) (2024)
- [Confident Learning: Estimating Uncertainty in Dataset Labels](https://mlsanity.com/paper/1911.00068/) (2019)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Binding Language Models in Symbolic Languages](https://mlsanity.com/paper/2210.02875/) (2022)
- [Universal Self-Consistency for Large Language Model Generation](https://mlsanity.com/paper/2311.17311/) (2023)
- [ChatDB: Augmenting LLMs with Databases as Their Symbolic Memory](https://mlsanity.com/paper/2306.03901/) (2023)
- [Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes](https://mlsanity.com/paper/2304.09433/) (2023)
- [MemoryArena: Benchmarking Agent Memory in Interdependent Multi-Session Agentic Tasks](https://mlsanity.com/paper/2602.16313/) (2026)
- [AMA-Bench: Evaluating Long-Horizon Memory for Agentic Applications](https://mlsanity.com/paper/2602.22769/) (2026)
- [Oolong: Evaluating Long Context Reasoning and Aggregation Capabilities](https://mlsanity.com/paper/2511.02817/) (2025)
- [MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search](https://mlsanity.com/paper/2604.17265/) (2026)
- [MINTEval: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems](https://mlsanity.com/paper/2605.18565/) (2026)
- [MemGym: a Long-Horizon Memory Environment for LLM Agents](https://mlsanity.com/paper/2605.20833/) (2026)
- [Memo-SQL: Structured Decomposition and Experience-Driven Self-Correction for Training-Free NL2SQL](https://mlsanity.com/paper/2601.10011/) (2026)
- [Understanding LLM Performance Degradation in Multi-Instance Processing: The Roles of Instance Count and Context Length](https://mlsanity.com/paper/2603.22608/) (2026)
- [Language models fail at extended rule following](https://mlsanity.com/paper/2605.02028/) (2026)

## 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.