ReTrace: Distilling Tool-Using Agents into Planner-Free Workflows
cs.AI, cs.LG, cs.MA
Submitted: 2026-11-10
Updated: 2026-11-10
Code: https://github.com/microsoft/Webwright
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- Program Learning with Verifiable Rewards: Distilling Expert Traces into Programs
- TraceCompiler: Skill-Guided Mining and Compilation of LLM Agent Traces into Mostly Deterministic Workflows
- SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
- De-Linearizing Agent Traces: Bayesian Inference of Latent Partial Orders for Efficient Execution
- SOPBench: Evaluating Language Agents at Following Standard Operating Procedures and Constraints
- STAGE: Stateful Translation to Agentic Graph Execution with Policy-Scoped Context and Deterministic Control
- Voyager: An Open-Ended Embodied Agent with Large Language Models
- Inducing Programmatic Skills for Agentic Tasks
- Trace2Policy: From Expert Behavior Traces to Self-Evolving Decision Agents
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents