# ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows

Source: [arXiv](https://arxiv.org/abs/2611.14492v1)  
Feed7 permalink: https://feed7.dev/p/2611-14492v1-1o3jd2l  
Published: 2026-11-10T18:49:47.000Z  
Trust: Needs Review (needs_review)

## Why Included

ReTrace turns logged agent runs into executable, planner-free workflows for repeated procedures. It trades a small amount of completion rate for lower cost and much shorter runtimes in the reported evaluations.

## Source Summary

ReTrace extracts decision rules from an SOP and logged agent runs, then compiles them into workflows where code selects each next step. Across **79 procedures**, completion was **93.8%** versus 96.8% for the agent, at 24% lower cost. On τ²-Bench, runtime was **1.3 seconds** versus 170 seconds for the agent.

## Practical Implication

For repeated, well-defined tasks, consider turning reliable agent traces into rules and workflows instead of asking a model to plan every run. The rule document can be compiled for different orchestration platforms.

## Agent-Ready Context

ReTrace extracts decision rules from an SOP and logged agent runs, then compiles them into workflows where code selects each next step. Across **79 procedures**, completion was **93.8%** versus 96.8% for the agent, at 24% lower cost. On τ²-Bench, runtime was **1.3 seconds** versus 170 seconds for the agent.

For repeated, well-defined tasks, consider turning reliable agent traces into rules and workflows instead of asking a model to plan every run. The rule document can be compiled for different orchestration platforms.

The workflow did not match the agent’s completion rate on the production procedures, and results varied by benchmark. On SOP-Bench, repair using labeled training failures raised performance to 87.8%; the paper’s results do not establish how well this approach handles changing procedures.

## Connected Context

Feed7 judgment across 1059 accumulated Signals:

ReTrace turns SOPs and logged runs into executable decision rules for repeated procedures, reducing runtime and cost while retaining slightly lower completion on production procedures than the agent. Its results support compiling stable workflows, with procedure changes and benchmark variation remaining important limits.

- [Can an Agent Debug a Web Corpus? Agentic Auditing of Slovak FineWeb2](https://feed7.dev/p/2610-31636v1-1i3iced) — Both put deterministic, reusable checks after agent-led discovery: ReTrace compiles observed procedures into workflows, while the corpus audit found static sampling more effective for validated selectors after agent exploration.
- [Tribal Dungeons of Global Shipping: AI Agents at Global Scale — Dmitry Buykin, Maersk](https://feed7.dev/p/tribal-dungeons-of-global-shipping-ai-agents-at-global-scale-dmitry-buyk-0kcigeh) — Both emphasize executable procedures and replayable traces as production reliability infrastructure; ReTrace adds evidence that logged runs and SOPs can be compiled into lower-cost workflows, while the Maersk account describes the operational correction system around such procedures.
- [Grow the Harness, Not the Context: From Strategy-Free Scaffolds to Reusable Specialist Agents](https://feed7.dev/p/2609-26760v1-0lklvan) — Both move recurring agent control into reusable code to reduce model work and cost. ReTrace compiles procedures from SOPs and runs, while Grow the Harness learns reusable control code and reports stable web-agent performance in its tested settings.

## Context Map

- Layer: agent
- Domains: coding, data
- Topics: harness-engineering, agent-reliability, tool-use

## Uncertainty

- The workflow did not match the agent’s completion rate on the production procedures, and results varied by benchmark. On SOP-Bench, repair using labeled training failures raised performance to 87.8%; the paper’s results do not establish how well this approach handles changing procedures.

## Agent Instruction

Use this item as source-backed context. Do not invent claims beyond the linked source. If this item conflicts with another source, call out the conflict.
