Beyond Compaction: Structured Context Eviction for Long-Horizon Agents
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
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget. We show that this context-management layer is a safety-critical failure surface: …
Practical Online KV Cache Compaction for LLM Agents: An Empirical Study
LLM agents accumulate long trajectories of reasoning steps, tool calls, and environment feedback, making the KV cache a major inference bottleneck. KV cache compaction can reduce this cost, but most prior methods assume …
TokenPilot: Cache-Efficient Context Management for LLM Agents
As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs. Existing approaches utilize text pruning or dynamic memory eviction to minimize token footprints; however, their uncons…
CompactionRL: Reinforcement Learning with Context Compaction for Long-Horizon Agents
Long-horizon agentic LLMs are increasingly limited by finite context windows, as extended interaction trajectories can exceed the maximum context length before a task is completed. Context compaction offers a natural sol…
Reinforcement LearningPagedEviction: Structured Block-wise KV Cache Pruning for Efficient Large Language Model Inference
KV caching significantly improves the efficiency of Large Language Model (LLM) inference by storing attention states from previously processed tokens, enabling faster generation of subsequent tokens. However, as sequence…