arXiv AI
Aug 13
Lost in Compaction: Evaluating Side-Constraint Loss under Context Compaction
arXiv:2608. 11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks.
Lost in Context Compaction: When LLM Systems Drop Side Constraints
Related stories
arXiv AI
Jun 30
Governance Decay: How Context Compaction Silently Erases Safety Constraints in Long-Horizon LLM Agents
arXiv:2606. 22528v2 Announce Type: replace Abstract: Modern LLM agents increasingly rely on context compaction, summarization, or eviction to keep long-running sessions within a token budget.
arXiv AI
Jul 13
Shared Selective Persistent Memory for Agentic LLM Systems
arXiv:2607. 09493v1 Announce Type: new Abstract: Agentic LLM systems that generate code through multi-turn tool use face a fundamental context problem: each session starts from zero, discarding the configuration choices, domain constraints, data schemas, and tool-use patterns that made previous sessions productive.
arXiv Computation and Language
Oct 23
When LLMs Forget What They Believe: Characterizing State Integrity Collapse in Long-Horizon Dialogues
The paper introduces the concept of State Integrity Collapse, where large language models remember a constraint but fail to apply it in later dialogue turns. It presents StateTrack‑Bench, a suite of controlled conversations testing numerical, format, role/persona, factual‑memory, and logical‑rule constraints across multiple model snapshots and dialogue depths. The study finds that while strict joint retention can be high, failures are largely due to behavioral drift rather than simple forgetting, and that reliability must be assessed over long‑horizon dialogues rather than single‑turn instruction following.
arXiv AI
Oct 9
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice
Agent-Controlled Forgetting for Tool-Using Agents: Reversible Context Curation in Practice explores a method where an agent selectively replaces detailed tool results with concise notes while archiving the originals for recovery. Using a Python harness, the approach reduces prompt tokens from 912,492 to 231,951 and cuts cumulative input tokens by 50%, yielding significant API cost savings. However, the method increases request count, slightly slows execution, and its effectiveness varies across different workloads.
arXiv AI
Oct 27
CTXAgent - Self-Controlled Context Management of LLM Agents
The paper introduces CTXAgent, a self‑controlled context management system for large language model agents that compacts conversation history when a token threshold is reached. It evaluates seven frontier models, comparing their ability to manage context with and without dedicated tools, and benchmarks performance across coding, scientific, and software engineering tasks. Results show that well‑managed models keep live context below 100k tokens, maintain high benchmark scores, and achieve significant cost reductions, with Claude Opus 5.5 outperforming its explicit configuration by 34% lower cost.
arXiv AI
Aug 26
When "Must" Becomes "Maybe": Constraint Weakening in LLM Agent Workflows
Large language model agents coordinate tasks via multi‑role, multi‑stage workflows that transform upstream state into intermediate artifacts such as summaries and plans. The study shows that when these artifacts are transformed—through compression, plan assimilation, or other handoff methods—the strict action‑binding constraints on upstream state can be weakened, turning mandatory requirements into optional information. In 1,296 synthetic episodes, direct handoff preserved all safety blockers, whereas transformed handoffs frequently deactivated or forbidden actions, but restoring full state fields or applying downstream verification can recover preservation.
arXiv AI
Oct 26
Benchmarks Are Surprisingly Compaction-Friendly
The paper investigates how context compaction—losing information to free up a language model’s context window—affects performance on long‑horizon agentic tasks. Using the OpenCode scaffold and five compaction strategies, the authors evaluate three frontier models on PaperBench, ProgramBench, and PostTrainBench, finding that compaction thresholds largely do not hurt performance for 1M‑context models, but can degrade GPT‑5.3‑Codex on certain benchmarks. The study also shows that compaction can silently drop critical task constraints, especially on ProgramBench and real user‑agent sessions from SWE‑chat, yet current benchmarks remain largely compaction‑friendly because objectives are fixed and progress is stored externally.
arXiv AI
Oct 26
Contextual Memory Virtualisation: DAG-Based State Management and Structurally Lossless Trimming for LLM Agents
arXiv:2602.22402v2 Announce Type: replace-cross Abstract: As large language models engage in extended reasoning tasks, they accumulate significant state -- architectural mappings, trade-off decisions...
Hugging Face Trending Papers
Jun 29
LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via a Proprioceptive Dashboard
Long-horizon tool agents are bottlenecked by how their context grows toward the limits of the context window. Recent systems make context management agent- or system-controlled, but they either learn a compression policy that discards evidence or manage context in a layer the agent never sees.
arXiv AI
Sep 16
Protocol-Preserving Context Trimming for Agentic Workflows: Benefits, Failure Regimes, and Budget Guardrails
The paper evaluates five context‑trimming strategies for agentic large language model workflows, comparing them on metrics such as task success, protocol adherence, token savings, and latency. Conventional trimming methods save about 60% of tokens but achieve lower success rates, while protocol‑aware trimming raises success to 92.2% and adaptive guardrails further improve it to 96% success with 56% token savings. The study shows that preserving protocol‑critical state is more important than aggressive token removal, and that adaptive guardrails enhance efficiency, scalability, and reliability for long‑horizon agentic systems.
arXiv AI
Jul 29
Addressable Recall Compaction for Long Context-Window Control in AI Agents
arXiv:2607. 25066v1 Announce Type: new Abstract: Long-horizon LLM agents accumulate reasoning traces, actions, and tool observations that can eventually exceed a model's fixed context window.