arXiv:2608. 11242v1 Announce Type: cross Abstract: When the context window is under pressure, LLM systems compact prior context to continue ongoing tasks.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
CliffCompaction is an autocompaction technique that reduces cost by up to 50% while maintaining or improving performance on benchmarks such as Terminal‑Bench and KernelBench. It achieves this by truncating or dropping content without rephrasing, ensuring compacted information remains faithful and preventing context drift. The method enables efficient test‑time scaling, matching or surpassing higher‑cost models like Opus 4.7 and GPT‑5.3 Codex, and delivers significant CUDA kernel speedups on KernelBench.
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.
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:2606. 17016v1 Announce Type: cross Abstract: As LLM agents are deployed in long-horizon sessions, context accumulation drives up inference costs.
arXiv:2608. 06503v1 Announce Type: new Abstract: Recurrent context compression controls context growth in long-horizon agents, but its behavioral effects remain poorly understood.
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.