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

• URL: http://arxiv.org/abs/2510.04618v1
• Date: Mon, 06 Oct 2025 09:30:18 GMT
• Title: Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
• Authors: 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,
• Abstract summary: We introduce ACE (Agentic Context Engineering), a framework that treats contexts as evolving playbooks.<n>Across agent and domain-specific benchmarks, ACE consistently outperforms strong baselines.<n> ACE could adapt effectively without labeled supervision and instead by leveraging natural execution feedback.
• Score: 18.829572148850563
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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. Building on the adaptive memory introduced by Dynamic Cheatsheet, 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.

Related papers

• Modular Prompt Optimization: Optimizing Structured Prompts with Section-Local Textual Gradients [0.8604557306886812]
  We introduce a schema-based prompt optimization framework that treats prompts as structured objects composed of fixed semantic sections.<n>We evaluate MPO on two reasoning benchmarks, ARC-Challenge and MMLU, using LLaMA-3 8B-Instruct and Mistral-7B-Instruct as solver models.
  arXiv  Detail & Related papers  (2026-01-07T16:20:08Z)
• SCOPE: Prompt Evolution for Enhancing Agent Effectiveness [53.75986399936395]
  Large Language Model (LLM) agents are increasingly deployed in environments that generate massive, dynamic contexts.<n>While agents have access to this context, their static prompts lack the mechanisms to manage it effectively.<n>We introduce textbfSCOPE (Self-evolving Context Optimization via Prompt Evolution)<n>We propose a Dual-Stream mechanism that balances tactical specificity (resolving immediate errors) with strategic generality (evolving long-term principles)
  arXiv  Detail & Related papers  (2025-12-17T12:25:05Z)
• Improving Language Agents through BREW [7.098644778864677]
  Large Language Model (LLM)-based agents are increasingly applied to tasks requiring structured reasoning, tool use, and environmental adaptation.<n>Current training paradigms for model weight optimization methods, like PPO and GRPO, remain relatively impractical with their high computational overhead for rollout convergence.<n>We introduce BREW, a framework for agent optimization for downstream tasks via construction and refinement.
  arXiv  Detail & Related papers  (2025-11-25T13:34:54Z)
• Sample-Efficient Online Learning in LM Agents via Hindsight Trajectory Rewriting [92.57796055887995]
  We introduce ECHO, a prompting framework that adapts hindsight experience replay from reinforcement learning for language model agents.<n> ECHO generates optimized trajectories for alternative goals that could have been achieved during failed attempts.<n>We evaluate ECHO on stateful versions of XMiniGrid, a text-based navigation and planning benchmark, and PeopleJoinQA, a collaborative information-gathering enterprise simulation.
  arXiv  Detail & Related papers  (2025-10-11T18:11:09Z)
• CoT Referring: Improving Referring Expression Tasks with Grounded Reasoning [67.18702329644526]
  CoT Referring enhances model reasoning across modalities through a structured, chain-of-thought training data structure.<n>We restructure the training data to enforce a new output form, providing new annotations for existing datasets.<n>We also integrate detection and segmentation capabilities into a unified MLLM framework, training it with a novel adaptive weighted loss to optimize performance.
  arXiv  Detail & Related papers  (2025-10-03T08:50:21Z)
• Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent [6.300669721057781]
  Meta-Policy Reflexion (MPR) is a framework that consolidates LLM-generated reflections into a structured, predicate-like Meta-Policy Memory (MPM)<n>MPR externalizes reusable corrective knowledge without model weight updates, enforces domain constraints to reduce unsafe or invalid actions, and retains the adaptability of language-based reflection.<n> Empirical results reported in the supplied material indicate consistent gains in execution accuracy and robustness when compared to Reflexion baselines; rule admissibility further improves stability.
  arXiv  Detail & Related papers  (2025-09-04T08:18:39Z)
• MeVe: A Modular System for Memory Verification and Effective Context Control in Language Models [0.0]
  MeVe is a novel modular architecture intended for Memory Verification and smart context composition.<n>MeVe rethinks the RAG paradigm by proposing a five-phase modular design that distinctly breaks down the retrieval and context composition process.<n>MeVe significantly improves context efficiency, achieving a 57% reduction on the Wikipedia dataset and a 75% reduction on the more complex HotpotQA dataset compared to standard RAG implementations.
  arXiv  Detail & Related papers  (2025-09-01T14:33:09Z)
• Reflection-Enhanced Meta-Optimization Integrating TextGrad-style Prompt Optimization with Memory-Driven Self-Evolution [0.0]
  We propose a framework that integrates a memory-augmented Reflection RetrievalRAG module and a Self-Adaptive meta-controller.<n>REMO achieves more stable and robust tuning, albeit at the cost of increased computational overhead.
  arXiv  Detail & Related papers  (2025-08-26T07:25:45Z)
• ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interaction [84.90394416593624]
  Agentic task-solving with Large Language Models (LLMs) requires multi-turn, multi-step interactions.<n>Existing simulation-based data generation methods rely heavily on costly autoregressive interactions between multiple agents.<n>We propose a novel Non-Autoregressive Iterative Generation framework, called ToolACE-MT, for constructing high-quality multi-turn agentic dialogues.
  arXiv  Detail & Related papers  (2025-08-18T07:38:23Z)
• Less is More: Empowering GUI Agent with Context-Aware Simplification [62.02157661751793]
  We propose a context-aware framework for building an efficient and effective GUI Agent, termed SimpAgent.<n>With the above components, SimpAgent reduces 27% FLOPs and achieves superior GUI navigation performances.
  arXiv  Detail & Related papers  (2025-07-04T17:37:15Z)
• Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence [131.41894248194995]
  We propose context-oriented decomposition adaptation (CorDA), a novel method that initializes adapters in a task-aware manner.<n>Thanks to the task awareness, our method enables two optional adaptation modes, knowledge-preserved mode (KPM) and instruction-previewed mode (IPM)
  arXiv  Detail & Related papers  (2025-06-16T07:55:14Z)
• PICASO: Permutation-Invariant Context Composition with State Space Models [98.91198288025117]
  State Space Models (SSMs) offer a promising solution by allowing a database of contexts to be mapped onto fixed-dimensional states.<n>We propose a simple mathematical relation derived from SSM dynamics to compose multiple states into one that efficiently approximates the effect of concatenating raw context tokens.<n>We evaluate our resulting method on WikiText and MSMARCO in both zero-shot and fine-tuned settings, and show that we can match the strongest performing baseline while enjoying on average 5.4x speedup.
  arXiv  Detail & Related papers  (2025-02-24T19:48:00Z)
• Towards more Contextual Agents: An extractor-Generator Optimization Framework [0.0]
  Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications.<n>However, their performance often degrades in context-specific scenarios, such as specialized industries or research domains.<n>To address this challenge, our work introduces a systematic approach to enhance the contextual adaptability of LLM-based agents.
  arXiv  Detail & Related papers  (2025-02-18T15:07:06Z)
• Entropy-Regularized Token-Level Policy Optimization for Language Agent Reinforcement [67.1393112206885]
  Large Language Models (LLMs) have shown promise as intelligent agents in interactive decision-making tasks. We introduce Entropy-Regularized Token-level Policy Optimization (ETPO), an entropy-augmented RL method tailored for optimizing LLMs at the token level. We assess the effectiveness of ETPO within a simulated environment that models data science code generation as a series of multi-step interactive tasks.
  arXiv  Detail & Related papers  (2024-02-09T07:45:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.