Paper page - SkillEvolBench: Benchmarking the Evolution from Episodic Experience to Procedural Skills

Source: https://huggingface.co/papers/2605.24117 Authors:

,

,

,

,

,

,

,

,

,

,

,

,

,

,

Abstract

Current large language model agents struggle to form robust reusable skills from episodic experience, with raw trajectory reuse often outperforming distilled skills due to discarded contextual cues.

Large language model (LLM) agents accumulate richepisodic trajectorieswhile solving real-world tasks, but it remains unclear whether such experience can be distilled into reusableprocedural skills. We introduce SkillEvolBench, adiagnostic benchmarkfor evaluating this step fromexperience reusetoskill formation. It contains 180 tasks across six real-world agent environments, organized intorole-conditioned task familieswith shared latent procedures. Agents learn from acquisition tasks, update an externalskill libraryusing compacted trajectories andverifier feedback, and then face frozen deployment tasks testing context shift, adversarial shortcuts, and composition. By comparing self-generated and curated-start skill evolution against no-skill and raw-trajectory controls, SkillEvolBench separatesprocedural abstractionfrom base capability, curated prior knowledge, and direct reuse of episodic traces. Across ten model configurations and three agent harnesses, we find that current agents often adapt locally but rarely form robust reusable skills.Skill-based conditionscan improve acquisition or replay, and individual models sometimes gain on specific deployment axes, but these gains are unstable under frozen deployment. Raw-trajectory reuse frequently outperforms distilled skills, suggesting that current abstraction procedures discard contextual and procedural cues that remain useful for future tasks. Capacity and cost analyses further show that writing more skills or larger Tier-3 resource libraries is not sufficient: additional updates can improve coverage while introducingepisode-specific driftandprocedural clutter. These findings position SkillEvolBench as a testbed for measuring when one-off experience becomes durable procedural knowledge rather than task-local memory.

View arXiv pageView PDFProject pageAdd to collection

Get this paper in your agent:

hf papers read 2605\.24117

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2605.24117 in a model README.md to link it from this page.

Datasets citing this paper0

No dataset linking this paper

Cite arxiv.org/abs/2605.24117 in a dataset README.md to link it from this page.

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2605.24117 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.