# Plans Don't Persist: Why Context Management Is Load Bearing for LLM Agents

arXiv: https://arxiv.org/abs/2606.22953 · HTML: https://mlsanity.com/paper/2606.22953/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 21 of its 26 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 21 of 21)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [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)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering](https://mlsanity.com/paper/1809.09600/) (2018)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Inference-Time Intervention: Eliciting Truthful Answers from a Language Model](https://mlsanity.com/paper/2306.03341/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Discovering Latent Knowledge in Language Models Without Supervision](https://mlsanity.com/paper/2212.03827/) (2022)
- [The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets](https://mlsanity.com/paper/2310.06824/) (2023)
- [Eliciting Latent Predictions from Transformers with the Tuned Lens](https://mlsanity.com/paper/2303.08112/) (2023)
- [LLMs Get Lost In Multi-Turn Conversation](https://mlsanity.com/paper/2505.06120/) (2025)
- [Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification](https://mlsanity.com/paper/2504.05419/) (2025)
- [Effectively Controlling Reasoning Models through Thinking Intervention](https://mlsanity.com/paper/2503.24370/) (2025)
- [ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning](https://mlsanity.com/paper/2510.15211/) (2025)
- [Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning](https://mlsanity.com/paper/2510.10494/) (2025)
- [From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models](https://mlsanity.com/paper/2509.23676/) (2025)

## Built on by (most cited first, 4 of 4)

- [LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception](https://mlsanity.com/paper/2606.30005/) (2026)
- [The Refusal Residue: When Probes Catch Alignment Faking and When They Don't](https://mlsanity.com/paper/2607.13346/) (2026)
- [The Horizon Gap: Planning, Memory, Execution, Training, and Evaluation for Long-Horizon LLM Agents](https://mlsanity.com/paper/2608.06663/) (2026)
- [The Default Trap: Rethinking Plan Evaluation in Tool-Using LLM Agents](https://mlsanity.com/paper/2609.36829/) (2026)

## Abstract (arXiv)

Context managers summarize or evict old messages so agents can operate beyond a finite window. This creates a reliability problem: removing history that still shapes the model's computation may change later actions, while retaining everything defeats compression. We study plans because agents create them early and are expected to use them later, yet behavioral success alone cannot reveal whether later calls still depend on the plan exchange. We make four contributions. First, we introduce replay pairing, which holds the action-observation trajectory fixed and compares pre-action hidden states with and without the plan exchange. We show that, on Llama-3.1-70B in ALFWorld, the mean contrast across 15 sampled layers decreases 4.1x from the first post-plan action to the second; Llama-3.1-8B shows a similar 5.6x decrease. Second, we show that a simple linear model using layer-32 hidden states predicts later contrast on entirely held-out tasks better than a baseline that only knows the action-call offset (R^2 = 0.847 vs. 0.575). Third, we identify confounds that limit this measurement: the paired histories differ in length, token positions, and discourse structure, and replayed reasoning can reintroduce plan-derived text. Reasoning traces therefore require symmetric controls, and native Qwen3 shows that the Llama timing pattern is not universal. Fourth, in a separate descriptive compression test, we find pooled ALFWorld run success of 56.7% with full history and 22.0% with naive eviction; preserving or re-surfacing only the plan does not recover the gap. Replay pairing measures sensitivity to retaining an exchange, not isolated plan content or later eviction. It gives researchers a concrete audit tool and suggests that context policies should preserve broader task state, not plans alone.