用有限状态机让AI自主进化，既灵活又可控。
EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
- 用显式状态机替代自由改写，分层优化流程与技能
- 在多跳问答任务中达58.0%准确率，优于固定流程
- 适合需要持续优化的开放性研究场景
尽管基于大模型的智能体在深度研究中展现潜力，但现有方法多依赖固定工作流，难以应对真实世界中的开放性问题。近期研究尝试通过自演化机制让智能体重写自身代码或提示词以提升求解能力，但无约束优化常引发不稳定性、幻觉和指令漂移。本文提出EvoFSM，一种结构化的自演化框架，通过演化显式的有限状态机（FSM）实现适应性与控制力的平衡。该框架将优化空间解耦为宏观流程（状态转移逻辑）与微观技能（状态特定行为），在明确的行为边界下实现精准改进。受批判机制引导，EvoFSM通过少量受限操作优化FSM，还引入自演化记忆，将成功轨迹提炼为可复用先验，失败模式作为未来查询的约束。在五个多跳问答基准上的实验证明其有效性，尤其在DeepSearch基准上达到58.0%准确率。交互式决策任务结果进一步验证其泛化能力。
原文摘要 · Abstract (English)
While LLM-based agents have shown promise for deep research, most existing approaches rely on fixed workflows that struggle to adapt to real-world, open-ended queries. Recent work therefore explores self-evolution by allowing agents to rewrite their own code or prompts to improve problem-solving ability, but unconstrained optimization often triggers instability, hallucinations, and instruction drift. We propose EvoFSM, a structured self-evolving framework that achieves both adaptability and control by evolving an explicit Finite State Machine (FSM) instead of relying on free-form rewriting. EvoFSM decouples the optimization space into macroscopic Flow (state-transition logic) and microscopic Skill (state-specific behaviors), enabling targeted improvements under clear behavioral boundaries. Guided by a critic mechanism, EvoFSM refines the FSM through a small set of constrained operations, and further incorporates a self-evolving memory that distills successful trajectories as reusable priors and failure patterns as constraints for future queries. Extensive evaluations on five multi-hop QA benchmarks demonstrate the effectiveness of EvoFSM. In particular, EvoFSM reaches 58.0% accuracy on the DeepSearch benchmark. Additional results on interactive decision-making tasks further validate its generalization.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。