Skip to content

CoEM: Empowering Long-Context Reasoning with Commit-on-Evidence Memory

Sep 2026 · arXiv.org · Vol abs/2609.36935 · 0 citations · 34 references
Computer Science

TL;DR

CoEM preserves potentially useful source excerpts verbatim in a pending set, allowing subsequent context to clarify their relevance before irreversible compression, and consistently improves long-context reasoning.

Abstract

Long-context reasoning is essential for complex and long-horizon tasks, yet the performance of large language models (LLMs) degrades as context length increases. Recent approaches address this by processing input chunk by chunk while maintaining a bounded textual memory in model context. However, premature information compression can discard critical details essential for subsequent reasoning. In this paper, we introduce Commit-on-Evidence Memory (CoEM), which learns when to convert source evidence into compact memory facts. Specifically, under a fixed context-memory budget, CoEM preserves potentially useful source excerpts verbatim in a pending set, allowing subsequent context to clarify their relevance before irreversible compression. As new context arrives, a learned policy revisits each pending excerpt and decides whether to promote it to the committed memory, retain it for further consideration, or discard it. A frozen verifier ensures proposed facts are accepted only if supported by retained excerpts and current context. To further guide effective memory management, we train this policy using reinforcement learning by combining fine-grained, step-level evidence rewards with final answer rewards. Extensive experiments demonstrate that CoEM consistently improves long-context reasoning. When evaluated on 6,400 documents long-context input, CoEM outperforms the strongest memory baseline by 10.4-11.4 F1 points on Qwen3.5-9B. Code repository: https://github.com/benmagnifico/CoEM.

View source

Similar papers

#artificial intelligence Preprint Oct 2026

Decoupling Memory from Context: Structured Memory for Token-Efficient Test-Time Continual Learning

This work introduces a unified formulation of context optimization and shows that an agent memory system update can be interpreted as an optimization update procedure over the model's context, and proposes GraphMemory, a lightweight graph-based memory that accumulates, refines, organizes, and connects reusable strategi...

Yehya Farhat, Michael Desmond, Anastasios Kyrillidis · 0 citations

Remember by Asking: Retrieval-Induced Memory Evolution for LLM Agents

RIME is introduced, a retrieval-induced memory framework that shifts memory construction from monolithic compression toward evidence-centered integration and consistently achieves the best performance across all three quality metrics among the compared methods, while requiring substantially fewer query-time LLM tokens.

Wan-Qi Zhou, Jia-Wei Lu, Yang Wang et al. · 0 citations

Towards Evolving Context Parameterization for Large Language Models

This work proposed PLUME, a training-free method that constructs a global update representation, activates memory evidence to form a local parameter view, and adaptively integrates their predictions during decoding, which demonstrated its effectiveness in sequential evolution settings.

Xiao Shi, Zhe-Rui Li, Yi-Ming Jiang et al. · 0 citations
#natural language process... Preprint Sep 2026

Compile, Don't Memorize: A Context Compilation Architecture (CCA) for In-Context Learning

The Context Compilation Architecture (CCA), whose central novelty is a typed intermediate representation (IR) with fixed slots (rules.{must_do, must_not, conditional}, output_spec, available_tools, data_profile) into which any prose context is compiled once; executable verifiers and a violation-gated correction loop fo...

Jin-Hu Qi, Min-Da Hu, Wen-Tao Zhang et al. · 0 citations
Preprint Aug 2026

LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation

The results suggest that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the granularity at which it is consolidated, and that the accuracy--cost trade-off of long-term agent memory depends not only on what information is retained, but also on the gra...

Dongfang Li, Zi-Xuan Liu, Junmai Wang et al. · 3 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.