paper-with-me

Papers

Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models

2025-10-06 · Qizheng Zhang, Changran Hu, Shubhangi Upasani, Boyuan Ma, Fenglu Hong, Vamsidhar Kamanuru, Jay Rainton, Chen Wu, Mengmeng Ji, Hanchen Li, Urmish Thakker, James Zou, Kunle Olukotun arxiv

Large language model (LLM) applications such as agents and domain-specific reasoning increasingly rely on context adaptation: modifying inputs with instructions, strategies, or evidence, rather than weight updates. Prior approaches improve usability but often suffer from brevity bias, which drops domain insights for concise summaries, and from context collapse, where iterative rewriting erodes details over time. We introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks that accumulate, refine, and organize strategies through a modular process of generation, reflection, and curation. ACE prevents collapse with structured, incremental updates that preserve detailed knowledge and scale with long-context models. Across agent and domain-specific benchmarks, ACE optimizes contexts both offline (e.g., system prompts) and online (e.g., agent memory), consistently outperforming strong baselines: +10.6% on agents and +8.6% on finance, while significantly reducing adaptation latency and rollout cost. Notably, ACE could adapt effectively without labeled supervision and instead by leveraging natural execution feedback. On the AppWorld leaderboard, ACE matches the top-ranked production-level agent on the overall average and surpasses it on the harder test-challenge split, despite using a smaller open-source model. These results show that comprehensive, evolving contexts enable scalable, efficient, and self-improving LLM systems with low overhead.

📄 PDF Abstract BibTeX arXiv:2510.04618

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Haystack Engineering: Context Engineering for Heterogeneous and Agentic Long-Context Evaluation

2025-10-08 · Mufei Li, Dongqi Fu, Limei Wang, Si Zhang 외 arxiv

Modern long-context large language models (LLMs) perform well on synthetic "needle-in-a-haystack" (NIAH) benchmarks, but such tests overlook how noisy contexts arise from biased retrieval and agentic workflows. We argue …

SEARL: Joint Optimization of Policy and Tool Graph Memory for Self-Evolving Agents

2026-04-09 · Xinshun Feng, Xinhao Song, Lijun Li, Gongshen Liu 외 arxiv

Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) have demonstrated significant potential in single-turn reasoning tasks. With the paradigm shift toward self-evolving agentic learning, models are i…

Reinforcement Learning

Self-Evolving Coding Agents

2026-08-04 · Hao Zhou, Haichuan Hu, Ye Shang, Quanjun Zhang hf

Large language models are increasingly embedded in software engineering workflows as coding agents that can inspect repositories, invoke tools, execute tests, debug failures, and generate patches. Yet most existing agent…

Meta Context Engineering via Agentic Skill Evolution

2026-01-29 · Haoran Ye, Xuning He, Vincent Arak, Haonan Dong 외 arxiv

The operational efficacy of large language models relies heavily on their inference-time context. This has established Context Engineering (CE) as a formal discipline for optimizing these inputs. Current CE methods rely …

Safe AI -- How is this Possible?

2022-01-25 · Harald Rueß, Simon Burton

Ttraditional safety engineering is coming to a turning point moving from deterministic, non-evolving systems operating in well-defined contexts to increasingly autonomous and learning-enabled AI systems which are acting …