# Evoflux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents

arXiv: https://arxiv.org/abs/2606.12674 · HTML: https://mlsanity.com/paper/2606.12674/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Tool learning and function calling, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Placed in

- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 12 of 12)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning](https://mlsanity.com/paper/2308.08747/) (2023)
- [Small Language Models are the Future of Agentic AI](https://mlsanity.com/paper/2506.02153/) (2025)
- [MCP-Bench: Benchmarking Tool-Using LLM Agents with Complex Real-World Tasks via MCP Servers](https://mlsanity.com/paper/2508.20453/) (2025)
- [Making Language Models Better Tool Learners with Execution Feedback](https://mlsanity.com/paper/2305.13068/) (2023)
- [AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization](https://mlsanity.com/paper/2602.20133/) (2026)
- [TinyAgent: Function Calling at the Edge](https://mlsanity.com/paper/2409.00608/) (2024)
- [From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents](https://mlsanity.com/paper/2603.22386/) (2026)

## Built on by (most cited first, 2 of 2)

- [FiMI Banking: A Sovereign Model for Indian Retail Banking](https://mlsanity.com/paper/2609.03960/) (2026)
- [Inherit-MAS: Test-Time Evolution of Multi-Agent Systems through Workflow and Execution Inheritance](https://mlsanity.com/paper/2610.02396/) (2026)

## Abstract (arXiv)

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.