dorsal/arxiv
View SchemaEvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines
| Authors | Shuo Zhang, Chaofa Yuan, Ryan Guo, Xiaomin Yu, Rui Xu, Zhangquan Chen, Zinuo Li, Zhi Yang, Shuhao Guan, Zhenheng Tang, Sen Hu, Liwen Zhang, Ronghao Chen, Huacan Wang |
|---|---|
| Categories | |
| ArXiv ID | 2601.09465vv1 |
| URL | https://arxiv.org/abs/2601.09465 |
| License | http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
Abstract
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.
{
"annotation_id": "5d4d7218-c0cd-4437-a09b-143469739108",
"date_created": "2026-02-17T05:53:20.411000Z",
"date_modified": "2026-02-17T05:53:20.411000Z",
"file_hash": "88efdb6488f5f7b7c9a1d4cf9c1863167ca85d0e5b03ac71662d16530ff62dba",
"private": false,
"record": {
"abstract": "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.",
"arxiv_id": "2601.09465",
"authors": [
"Shuo Zhang",
"Chaofa Yuan",
"Ryan Guo",
"Xiaomin Yu",
"Rui Xu",
"Zhangquan Chen",
"Zinuo Li",
"Zhi Yang",
"Shuhao Guan",
"Zhenheng Tang",
"Sen Hu",
"Liwen Zhang",
"Ronghao Chen",
"Huacan Wang"
],
"categories": [
"cs.AI"
],
"license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
"title": "EvoFSM: Controllable Self-Evolution for Deep Research with Finite State Machines",
"url": "https://arxiv.org/abs/2601.09465",
"version": "v1"
},
"schema_id": "dorsal/arxiv",
"source": {
"execution_id": "d7249260-89bf-46f4-b2f7-3b9ef4b72f47",
"id": "arXiv Dataset",
"type": "Model",
"variant": "snapshot-2026-01-17",
"version": "0.1.0"
},
"user_id": 1000002
}