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.
By Thang Dang, Yuma Ichikawa, Sakina Fatima, Koichi Shirahata
The paper "Token Optimization and Context Window Management in Multi‑Agent AI Workflows" introduces a practitioner framework that reduces token usage and latency in multi‑agent AI systems. It outlines six patterns—context stratification, fetch‑once/process‑locally architecture, schema‑contracted prompts, token‑aware fallback chains, semantic caching, and inter‑agent communication compression—and reports a 60‑70% token reduction and a 61‑116 second cold‑load latency improvement in production. A controlled study on relevance‑contrast context shows that mixing high‑ and low‑relevance items in prompts can improve relevance accuracy by up to +0.084.
whyItMatters":"The work provides concrete, repeatable engineering patterns that bridge research and production, enabling faster, cheaper, and more reliable AI workflows."
By Dvir Shamay
arXiv:2607. 21503v1 Announce Type: new Abstract: Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs.
By Gaurav Dadhich
arXiv:2608.29363v1 Announce Type: new
Abstract: Enterprise data agents answer business queries by chaining many tool calls over multiple reasoning steps, routinely accumulating hundreds of thousands...
By Ziqi Lin, Ye Wu, Mengying Yang, Xu Liu, Yizhou Liu, Qiang Ke, Qin Guo
Production AI agents' failures are less often due to an inability to reason well and more often because they cannot manage what is in their reasoning context: conversation histories, large prompts, large tool definitions, and ballooning tool outputs. Agents drown in their own accumulating history while paying a token cost that grows every turn, producing missing recalls within and across conversations.
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.
By Harish Gaggar