← 研踪 PaperTrailACL Anthology · ACL 2026:acl:2026.acl-long.754 · 记录 #1
Evolving Agents
来源日期（仅到月份） 2026-07
来源记录日期 2026-07
雷达观测 2026-11-01 22:00
摘要
AI agents powered by LLMs plan, reason and use tools well, but remain brittle to adapt and evolve because they fail to abstract the mechanisms underlying problem-solving. Reasoning, memory, and decision-making remain fragmented, leaving the systematic reuse of experience for adaptation at scale out of reach. In this paper, we introduce EvA (Evolving Agents), a framework to improve evolution in agentic reasoning that leverages quasi-symbolic abstractions—semi-structured dynamic representations that furnish constructs to distil and reuse reasoning mechanisms. They are learned and refined through experience, and when instantiated, deliver meta-states for organising reasoning. EvA orchestrates this mechanism via a Perceptor modelling observation and action, an Actor conditioning its policy on these abstractions, and a Controller overseeing structure to explore paths or initiate rollbacks. As experience accumulates, EvA refines both its abstractions and the modules that construct and instantiate them by learning past trajectories into reusable mechanisms. Our initial analysis shows that EvA improves accuracy and adapts under mid-episode distribution shifts that cause agents to plateau on complex reasoning and interactive planning tasks. These results position EvA as a step towards adaptive reasoning, memory, and meta-control.
论文发现出处
这些页面提供论文线索，不代表同行评审或质量认证。
观测到的版本
平台记录号代表本站观测到的元数据变化，不是作者修订号。来源日期仅到月份或年份时，按该月或该年首日存档。
记录 #1 · 2026-07 · 最新观测版本
Evolving Agents
AI agents powered by LLMs plan, reason and use tools well, but remain brittle to adapt and evolve because they fail to abstract the mechanisms underlying problem-solving. Reasoning, memory, and decision-making remain fragmented, leaving the systematic reuse of experience for adaptation at scale out of reach. In this paper, we introduce EvA (Evolving Agents), a framework to improve evolution in agentic reasoning that leverages quasi-symbolic abstractions—semi-structured dynamic representations that furnish constructs to distil and reuse reasoning mechanisms. They are learned and refined through experience, and when instantiated, deliver meta-states for organising reasoning. EvA orchestrates this mechanism via a Perceptor modelling observation and action, an Actor conditioning its policy on these abstractions, and a Controller overseeing structure to explore paths or initiate rollbacks. As experience accumulates, EvA refines both its abstractions and the modules that construct and instantiate them by learning past trajectories into reusable mechanisms. Our initial analysis shows that EvA improves accuracy and adapts under mid-episode distribution shifts that cause agents to plateau on complex reasoning and interactive planning tasks. These results position EvA as a step towards adaptive reasoning, memory, and meta-control.
查看此版本解读 →查看此版本原文 ↗