arXiv — cs.AI preprintsInternational16 October 2026
EvoFlux: Inference-Time Evolution of Executable Tool Workflows for Compact Agents
This is an official announcement record
Firsthand records what arXiv — cs.AI preprints announced and links to the original. The wording below is theirs, not ours.
arXiv:2606.12674v2 Announce Type: replace 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 missin
Read the official announcement
Opens arxiv.org
More from arXiv — cs.AI preprints
- The World Won't Wait: Evaluating and Teaching Agents Under a Live Clock16 October 2026
- Evaluating Model Capabilities After Benchmark Saturation16 October 2026
- Value-Informed Schedule Trimming for Accelerated Sequential Monte Carlo Guidance in Discrete Diffusion16 October 2026
- AlphaDiana: A Measurement System for Agents in Verifiable Reasoning Tasks16 October 2026
- When Correctness Feedback Erases Evidence: Phase-Separated Completeness Auditing in Verus16 October 2026
This content is for informational purposes only and is not professional advice. Specifications, prices, plan tiers, and features change frequently and may differ from what is shown here; verify current details on the manufacturer's or company's official page before purchasing. Ratings are based on analysis of published documentation, not independent lab testing.