SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills

• URL: http://arxiv.org/abs/2606.26669v1
• Date: Thu, 25 Jun 2026 07:02:32 GMT
• Title: SKILL-DISCO: Distilling and Compiling Agent Traces into Reusable Procedural Skills
• Abstract summary: We introduce SkillDisCo, a framework that distills reusable PFSM subgraphs from successful traces and compiles them into callable, executable, and verifiable procedural skills.<n> Experiments on ALFWorld and WebArena show that SkillDisCo improves success rates and reduces agent turns across benchmarks and model scales.
• Score: 4.661552076545078
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agents often repeatedly solve similar task instances from scratch, leading to unnecessary reasoning cost and long execution traces. Prior work has explored workflow reuse and executable skill induction, but it remains unclear which task scenarios admit procedural skills and how the shared procedural structure should be represented across successful traces. We study this problem in FSM-defined scenarios, where successful traces can be viewed as paths in an unknown transition graph, and formulate procedural skills as reusable parameterized control-flow subgraphs. Based on this view, we introduce SkillDisCo, a distillation-and-compilation framework that distills reusable PFSM subgraphs from successful traces and compiles them into callable, executable, and verifiable procedural skills. Experiments on ALFWorld and WebArena show that SkillDisCo improves success rates and reduces agent turns across benchmarks and model scales, demonstrating the benefits of representing shared experience as reusable execution structures.

Related papers

• Trace2Tower: Transition-Aware EigenTrace Induction of Multi-Level Skills for LLM Agents [8.640998417745086]
  We introduce Trace2Tower, a transition-aware EigenTrace framework that distills raw trajectories into a robust skill hierarchy.<n>Through a novel contrastive spectral decomposition, it isolates stable, success-aligned behavioral modes while rigorously suppressing failure-prone shortcuts.<n>On ALFWorld, Trace2Tower achieves 87.31% success requiring only 10.35 steps and 0.26 invalid actions; on WebShop, it reaches 50.67% exact success.
  arXiv  Detail & Related papers  (2026-09-04T15:22:39Z)
• EASy: Towards Efficient LLM-Based Agentic System [54.10819421625103]
  We propose EASy, a trainable agentic framework that jointly optimize task performance and computational efficiency through reinforcement learning.<n> EASy equips an LLM-based orchestrator with explicit knowledge of the capability and cost profiles of heterogeneous executors, enabling context-sensitive coordination beyond performance-only routing.<n>It further introduces a milestone-plan-act workflow that decomposes complex tasks into manageable milestones, constructs dependency-aware execution graphs, assigns suitable executors, and parallelizes independent steps while adapting subsequent decisions to intermediate outcomes.
  arXiv  Detail & Related papers  (2026-08-05T08:50:36Z)
• Anything2Skill: Compiling External Knowledge into Reusable Skills for Agents [27.965275812765015]
  Anything2Skill is a taxonomy-guided framework that compiles heterogeneous external knowledge into reusable, retrievable, and executable skills for agents.<n>We show that Anything2Skill combined with RAG achieves 98.85% and 94.10% success rates, respectively.
  arXiv  Detail & Related papers  (2026-06-08T10:24:32Z)
• Workflow-to-Skill: Skill Creation via Routing-Workflow-Semantics-Attachments Decomposition [24.535904687887236]
  This paper studies automatic Skill construction from heterogeneous interaction evidence, including demonstrations, agent trajectories, tool traces, and execution logs.<n>We argue that trace-to-skill construction is not simple summarization tasks, because traces are fragmented, redundant, and may miss rare but safety-critical behaviors.<n>We propose W2S, a framework that segments traces, induces local Skill drafts, aligns shared structures, reconciles branches, and compresses redundancy while preserving evidence and confidence annotations.
  arXiv  Detail & Related papers  (2026-06-05T04:19:57Z)
• COLLEAGUE.SKILL: Automated AI Skill Generation via Expert Knowledge Distillation [58.84646485020439]
  We present an automated trace-to-skill distillation system for generating person-grounded AI skills.<n> COLLEAGUE.SKILL produces a versioned skill package with two tracks: a capability track for practices, mental models, and decisions, and a bounded behavior track for communication style, interaction rules, and correction history.
  arXiv  Detail & Related papers  (2026-05-29T12:59:08Z)
• SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills [31.23929961213889]
  Large language model (LLM) agents accumulate rich episodic trajectories while solving real-world tasks.<n>We introduce SkillEvolBench, a diagnostic benchmark for evaluating this step from experience reuse to skill formation.<n>We find that current agents often adapt locally but rarely form robust reusable skills.
  arXiv  Detail & Related papers  (2026-05-22T18:23:31Z)
• ProcMEM: Learning Reusable Procedural Memory from Experience via Non-Parametric PPO for LLM Agents [31.24386037416211]
  LLM-driven agents often rely on on-the-fly reasoning, re-deriving solutions even in recurring scenarios.<n>This insufficient experience reuse leads to computational redundancy and execution instability.<n>We propose ProcMEM, a framework that enables agents to autonomously learn procedural memory from interaction experiences without parameter updates.
  arXiv  Detail & Related papers  (2026-02-02T09:43:12Z)
• PADME: Procedure Aware DynaMic Execution [7.8148770419284865]
  We introduce Procedure Aware DynaMic Execution (PADME), an agent framework that produces and exploits a graph-based representation of procedures.<n>Unlike prior work that relies on manual graph construction or unstructured reasoning, PADME autonomously transforms procedural text into executable graphs.<n>PADME achieves state-of-the-art performance on four diverse benchmarks, including ALFWorld and ScienceWorld.
  arXiv  Detail & Related papers  (2025-10-13T11:15:49Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement [50.481380478458945]
  Iterative step-level Process Refinement (IPR) framework provides detailed step-by-step guidance to enhance agent training. Our experiments on three complex agent tasks demonstrate that our framework outperforms a variety of strong baselines.
  arXiv  Detail & Related papers  (2024-06-17T03:29:13Z)
• SkillDiffuser: Interpretable Hierarchical Planning via Skill Abstractions in Diffusion-Based Task Execution [75.2573501625811]
  Diffusion models have demonstrated strong potential for robotic trajectory planning. generating coherent trajectories from high-level instructions remains challenging. We propose SkillDiffuser, an end-to-end hierarchical planning framework.
  arXiv  Detail & Related papers  (2023-12-18T18:16:52Z)
• Chain of Thought Imitation with Procedure Cloning [129.62135987416164]
  We propose procedure cloning, which applies supervised sequence prediction to imitate the series of expert computations. We show that imitating the intermediate computations of an expert's behavior enables procedure cloning to learn policies exhibiting significant generalization to unseen environment configurations.
  arXiv  Detail & Related papers  (2022-05-22T13:14:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.