# Beyond Compaction: Structured Context Eviction for Long-Horizon Agents

arXiv: https://arxiv.org/abs/2606.11213 · HTML: https://mlsanity.com/paper/2606.11213/

## Key facts

- Cited by 8 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 10 of its 17 references that are in the map.
- First posted on arXiv 1 May 2026.

## Placed in

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

## Builds on (most cited first, 10 of 10)

- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory](https://mlsanity.com/paper/2504.19413/) (2025)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Scaling Long-Horizon LLM Agent via Context-Folding](https://mlsanity.com/paper/2510.11967/) (2025)
- [ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization](https://mlsanity.com/paper/2509.13313/) (2025)
- [The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management](https://mlsanity.com/paper/2508.21433/) (2025)
- [LongCLI-Bench: A Preliminary Benchmark and Study for Long-horizon Agentic Programming in Command-Line Interfaces](https://mlsanity.com/paper/2602.14337/) (2026)

## Built on by (most cited first, 8 of 8)

- [Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents](https://mlsanity.com/paper/2606.22528/) (2026)
- [LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception](https://mlsanity.com/paper/2606.30005/) (2026)
- [Cost-Utility Alignment in LLM Agent Trajectories:Profiling,Attribution,Diagnosis,Adaptation,and Evaluation](https://mlsanity.com/paper/2608.26195/) (2026)
- [Handover of In-Context Learning State Across Session Boundaries](https://mlsanity.com/paper/2608.14528/) (2026)
- [What Eviction Destroys: A Restore-Counterfactual Audit of Forgetting in Agent Memory](https://mlsanity.com/paper/2609.08279/) (2026)
- [CliffCompaction: Cost-Efficient Compaction for Long-Horizon Coding Agents](https://mlsanity.com/paper/2609.26779/) (2026)
- [When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression](https://mlsanity.com/paper/2609.29875/) (2026)
- [Scaling Multi-Agent Intelligence with Substrate-Centric Coordination](https://mlsanity.com/paper/2610.16120/) (2026)

## Abstract (arXiv)

We present Context Window Lifecycle (CWL), a context-management scheme that gives long-horizon LLM agents an effectively unbounded working horizon. As a session accumulates history, CWL keeps the context within budget through graduated, semantically-aware eviction: the agent annotates its trajectory as typed, dependency-linked episodes as work proceeds, and a deterministic, LLM-free policy evicts content in priority order within that structure when a token budget is exceeded. CWL preserves user turns and the exploratory context the agent is actively reasoning over, while aggressively shedding action episodes whose effects are already persisted in the environment, keeping active context near a stable ceiling that also avoids the performance degradation associated with very large prompts. Compared to summarization-based compaction, CWL avoids four well-known limitations: unpredictable lossiness, destruction of causal structure, blocking model cost, and compression-induced hallucination. Compared to recency truncation, CWL is semantically aware: it drops the oldest-and-most-recoverable content according to the dependency graph rather than oldest-in-time regardless of relevance. We describe the annotation protocol, the episode graph, the eviction policy, and the token-accounting loop, and evaluate CWL on long-horizon agentic benchmarks: a single agent session completing 89 sequential tasks across 80 million tokens with no measurable degradation in task accuracy relative to per-task isolated sessions