# When Agent Context Goes Stale: Incoherence in Volatile Agent Context

arXiv: https://arxiv.org/abs/2610.05281 · HTML: https://mlsanity.com/paper/2610.05281/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 4 Oct 2026.

## Builds on (most cited first, 14 of 14)

- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [OpenHands: An Open Platform for AI Software Developers as Generalist Agents](https://mlsanity.com/paper/2407.16741/) (2024)
- [STALE: Can LLM Agents Know When Their Memories Are No Longer Valid?](https://mlsanity.com/paper/2605.06527/) (2026)
- [Supersede: Diagnosing and Training the Memory-Update Gap in LLM Agents](https://mlsanity.com/paper/2606.27472/) (2026)
- [Effective Strategies for Asynchronous Software Engineering Agents](https://mlsanity.com/paper/2603.21489/) (2026)
- [CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code Generation](https://mlsanity.com/paper/2510.18893/) (2025)
- [Self-GC: Self-Governing Context for Long-Horizon LLM Agents](https://mlsanity.com/paper/2607.00692/) (2026)
- [InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents](https://mlsanity.com/paper/2601.03204/) (2026)
- [Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems](https://mlsanity.com/paper/2606.17182/) (2026)
- [Multi-agent Collaboration with State Management](https://mlsanity.com/paper/2605.20563/) (2026)
- [ConflictRAG: Detecting and Resolving Knowledge Conflicts in Retrieval Augmented Generation](https://mlsanity.com/paper/2605.17301/) (2026)
- [When Agents Overtrust Environmental Evidence: An Extensible Agentic Framework for Benchmarking Evidence-Grounding Defects in LLM Agents](https://mlsanity.com/paper/2605.08828/) (2026)
- [Less Context, More Accuracy: A Bi-Temporal Memory Engine for LLM Agents Where a Lean Retrieved Context Beats the Full History](https://mlsanity.com/paper/2606.09900/) (2026)

## Abstract (arXiv)

Modern agents increasingly ground their reasoning in observations returned by tools, such as file contents read from a workspace. However, the data sources underlying these observations may later be modified by users, other agents, or external tools, while the model retains only the stale content in its context window. Existing agent runtimes provide little support for notifying the model that a previously observed fact has become stale, causing agents to reuse outdated observations and make incorrect claims about the current workspace state. We propose Concord, a context coherence framework that maintains the consistency between tool observation in agent context and the mutable sources from which they were derived. Concord links each observation to its source, detects source changes, and uses configurable handling policies to update, annotate, or suppress stale context before reuse. Concord is applicable across different agent runtimes and external resources, and can be easily extended to new runtime-resource settings. We implement Concord as a general framework, and instantiate a concrete use case to assess its effectiveness. We construct ConcordBench, where previously observed file contents become stale after subsequent edits. Across three evaluated frontier models, Concord produces answers consistent with the restored workspace state in all evaluated cases under these constructed conditions, matching the oracle on recover count for this benchmark, while using 46.4% fewer tokens than the strongest non-oracle baseline.