arXiv cs.AI· Kushal Raj Bhandari, Ling Yue, Ching-Yun Ko, Dhaval Patel, Shaowu Pan, Pin-Yu Chen, Jianxi Gao·· 2 天前AI 评分32
EvoFlux：面向小型智能体的可执行工具工作流推理时进化
EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
AI 导读
EvoFlux 是一种推理时搜索方法，通过对工具调用与依赖的结构化图进行进化循环来修复工具计划，并利用真实工具服务器的执行错误指导替换工具、修正参数、插入缺失步骤和删除冗余步骤。
正文 · 原文
Abstract:Small language models (1.5B-4B parameters) offer low-cost, low-latency tool use but often produce plausible plans that fail during execution due to unavailable tools, missing arguments, or broken dependencies. We introduce EvoFlux, an inference-time search method that repairs tool plans through an evolutionary loop over structured graphs of tool calls and dependencies. EvoFlux executes candidate plans against live tool servers and uses execution errors to guide targeted edits, including replacing tools, correcting parameters, inserting missing steps, and removing redundant ones. On held-out MCP-Bench tasks spanning 28 live servers and 250 tools, EvoFlux improves execution success from roughly 3% to 17-24% across four small planners. SFT and SFT+DPO trained on the same 177 demonstrations and 624 preference pairs match or underperform the zero-shot baseline, while ReAct reaches higher peaks on stronger planners at 4-20x greater planner-token cost per solved task. Execution-guided inference-time repair reliably improves small tool-using agents when supervision is limited.
| Comments: | Code is available at this https URL |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2606.12674 [cs.AI] |
| (or arXiv:2606.12674v2 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2606.12674 arXiv-issued DOI via DataCite |
Submission history
From: Kushal Raj Bhandari [view email]
[v1]
Wed, 10 Jun 2026 21:01:06 UTC (2,172 KB)
[v2]
Wed, 14 Oct 2026 21:02:23 UTC (3,348 KB)
来源：arXiv cs.AI · arxiv.org