A multimodal resource-to-skill pipeline converts tutorial videos and other human-created materials into a hierarchical skill wiki, improving software-agent artifact quality by an average of 11.9 points across seven authoring domains.
SkillFlow:Benchmarking Lifelong Skill Discovery and Evolution for Autonomous Agents
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
abstract
As the capability frontier of autonomous agents continues to expand, they are increasingly able to complete specialized tasks through plug-and-play external skills. Yet current benchmarks mostly test whether models can use provided skills, leaving open whether they can discover skills from experience, repair them after failure, and maintain a coherent library over time. We introduce SkillFlow, a benchmark of 166 tasks across 20 families in which task construction within each family follows a Domain-Agnostic Execution Flow (DAEF) that defines an agent workflow framework, allowing these tasks to share a consistent workflow. Agents are evaluated under an Agentic Lifelong Learning protocol in which they begin without skills, solve tasks sequentially within each family, externalize lessons through trajectory- and rubric-driven skill patches, and carry the updated library forward. Experiments reveal a substantial capability gap. For Claude Opus 4.6, lifelong skill evolution improves task success from 62.65% to 71.08% (+8.43 points). However, high skill usage does not necessarily imply high utility: Kimi K2.5 gains only +0.60 points despite 66.87% skill usage, while Qwen-Coder-Next reaches only a 44.58% task completion rate and still regresses relative to the vanilla setting. SkillFlow contributes a structured testbed for this direction and an in-depth empirical analysis of skill discovery, patching, transfer, and their failure modes under lifelong evaluation.
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
background 1representative citing papers
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
SkillCoach introduces self-evolving rubrics derived from rollouts to evaluate and supervise four process dimensions of agentic skill-use separately from outcome success.
ASPIRE uses code-as-policy, closed-loop execution traces for autonomous repair, a distilling skill library, and evolutionary search to discover persistent robot skills that transfer across tasks, simulation, real robots, and embodiments, reporting large gains over priors on manipulation benchmarks.
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.
citing papers explorer
-
RESOURCE2SKILL: Distilling Executable Agent Skills from Human-Created Multimodal Resources
A multimodal resource-to-skill pipeline converts tutorial videos and other human-created materials into a hierarchical skill wiki, improving software-agent artifact quality by an average of 11.9 points across seven authoring domains.
-
Co-Evolving Skill Generation and Policy Optimization
Framework estimates context-dependent marginal utility of candidate skills via reward gaps in matched base vs. skill-augmented rollouts to filter skills and co-train policy as generator.
-
SkillCoach: Self-Evolving Rubrics for Evaluating and Enhancing Agentic Skill-Use
SkillCoach introduces self-evolving rubrics derived from rollouts to evaluate and supervise four process dimensions of agentic skill-use separately from outcome success.
-
ASPIRE: Agentic /Skills Discovery for Robotics
ASPIRE uses code-as-policy, closed-loop execution traces for autonomous repair, a distilling skill library, and evolutionary search to discover persistent robot skills that transfer across tasks, simulation, real robots, and embodiments, reporting large gains over priors on manipulation benchmarks.
-
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
SkillsVote is a governance system for agent skills that profiles corpora, recommends via search, and gates updates on successful reusable outcomes, yielding benchmark gains without model changes.