Folio is a context manager for long‑horizon language agents that records and folds conversation history into three linked levels—short turn notes, event manifests, and source records—allowing efficient recovery without re‑reading the entire history. By programmatically selecting coarser views for older turns and providing handles for recovery tools, Folio reduces the need for model‑written compaction and lowers runtime costs. In benchmark tests, Folio solved 66 out of 75 tasks, outperforming other compaction methods and cutting working time and cost by roughly half.
arXiv:2608.21690v1 Announce Type: new
Abstract: LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier i...
By Yin Lin, Elaine Ang, Erkang Zhu, Bolin Ding, Jingren Zhou
LLM agents increasingly take on long-running tasks whose history grows far beyond a single model context window. Existing approaches compress earlier interactions or extract selected information into...
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.
By Matthias Busch, Marius Tacke, Roland C. Aydin, Christian Feiler, Christian J. Cyron
The paper introduces LOHA, a context layout that compresses older tool observations into soft tokens while keeping the agent’s own turns and the last K observations in plain text, and ACD, a training method that distills full‑text predictions into this latent representation while anchoring behavior on plain text. This approach reduces context per call by up to 57% without significant loss in resolve rates, and improves instance throughput in single‑GPU serving. Experiments on SWE‑bench Verified show that K=3 yields a 43–57% compression with only modest performance impact, while larger windows favor task performance over compression.
By Zhensheng Zou (Peking University), Guoqing Wang (Peking University), Dan Hao (Peking University)
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.
By Jeanne Salle, Hardik Bhatnagar, Matthias Bethge, Sahar Abdelnabi, Maksym Andriushchenko