SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks

• URL: http://arxiv.org/abs/2604.20087v1
• Date: Wed, 22 Apr 2026 01:07:37 GMT
• Title: SkillLearnBench: Benchmarking Continual Learning Methods for Agent Skill Generation on Real-World Tasks
• Abstract summary: We introduce SkillLearnBench, the first benchmark for evaluating continual skill learning methods.<n>Continual learning improves tasks with clear, reusable but struggles on open-ended tasks.<n>Our data and code are open-source at https://github.com/cscmu/SkillLearnBench.
• Score: 32.195367070060904
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Skills have become the de facto way to enable LLM agents to perform complex real-world tasks with customized instructions, workflows, and tools, but how to learn them automatically and effectively remains unclear. We introduce SkillLearnBench, the first benchmark for evaluating continual skill learning methods, comprising 20 verified, skill-dependent tasks across 15 sub-domains derived from a real-world skill taxonomy , evaluated at three levels: skill quality, execution trajectory, and task outcome. Using this benchmark, we evaluate recent continual learning techniques, those leveraging one-shot, self/teacher feedback, and skill creator to generate skills from agent experiences. We find that all continual learning methods improve over the no-skill baseline, yet consistent gains remain elusive: no method leads across all tasks and LLMs, and scaling to stronger LLMs does not reliably help. Continual learning improves tasks with clear, reusable workflows but struggles on open-ended tasks, and using stronger LLM backbones does not consistently produce better skills. Our analysis also revealed that multiple iterations in continual learning facilitate genuine improvement via external feedback, whereas self-feedback alone induces recursive drift. Our data and code are open-source at https://github.com/cxcscmu/SkillLearnBench to enable further studies of automatic skill generation and continual learning techniques.

Related papers

• PRACTICE: From Experience to Expertise in Self-Evolving Embodied Agents [8.367852606377419]
  We train a skill learner to discover and maintain a persistent skill library from past interaction trajectories.<n>We apply online skill-edit distillation to align the skill learner with a stronger teacher on its current edit distribution.<n>Experiments demonstrate that a compact skill learner delivers consistent performance improvements across successive library-update rounds.
  arXiv  Detail & Related papers  (2026-08-31T13:26:16Z)
• Evo-Harness: Context-to-Harness Skill Compilation for Self-Evolving Agents [67.97365535829098]
  Learning from experience is critical for developing capable, self-improving large language model (LLM) agents.<n>We propose Evo-Harness, which distills noisy, single-shot executions into reusable skill harnesses for cross-domain and topic-level adaptation.<n>Our analysis demonstrates the effectiveness of Evo-Harness and provides a principled understanding of how LLM agents can effectively learn on the fly.
  arXiv  Detail & Related papers  (2026-08-15T06:43:56Z)
• SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution [39.74364990208475]
  Large language model agents often encounter related yet distinct tasks that share reusable solution patterns.<n>We introduce SkillRise, a unified reinforcement learning framework for learning skills across tasks.
  arXiv  Detail & Related papers  (2026-07-29T11:26:33Z)
• Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills [53.15216425100295]
  We introduce Skill Self-Play (Skill-SP), a co-evolutionary framework comprising a proposer, a solver, and a skill controller.<n>The proposer generates challenging tasks conditioned on dynamically sampled skills; the solver explores candidate solutions to push its capability boundaries; and the skill controller collects execution feedback to update and expand the skill library.<n>This interactive co-evolution effectively bridges the gap between structured verification and open-ended exploration.
  arXiv  Detail & Related papers  (2026-07-24T17:59:22Z)
• SkillOS: Learning Skill Curation for Self-Evolving Agents [67.94374107466957]
  We propose SkillOS, an experience-driven RL training recipe for learning skill curation in self-evolving agents.<n>SkillOS pairs a frozen agent executor that retrieves and applies skills with a trainable skill curator that updates an external SkillRepo from accumulated experience.<n>We show that SkillOS consistently outperforms memory-free and strong memory-based baselines in both effectiveness and efficiency.
  arXiv  Detail & Related papers  (2026-05-07T17:31:50Z)
• SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization [61.37478254738943]
  Inference-time skill augmentation is fundamentally limited.<n>We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization.<n>SKILL0 achieves substantial improvements over the standard RL baseline.
  arXiv  Detail & Related papers  (2026-04-02T17:03:05Z)
• Reinforcement Learning for Self-Improving Agent with Skill Library [14.717149089634718]
  Large Language Model (LLM)-based agents have demonstrated remarkable capabilities in complex reasoning and multi-turn interactions.<n>One promising approach is implementing skill libraries that allow agents to learn, validate, and apply new skills.<n>We propose a Reinforcement Learning (RL)-based approach to enhance agents' self-improvement capabilities with a skill library.
  arXiv  Detail & Related papers  (2025-12-18T21:58:19Z)
• Self-Tuning: Instructing LLMs to Effectively Acquire New Knowledge through Self-Teaching [67.11497198002165]
  Large language models (LLMs) often struggle to provide up-to-date information.<n>Existing approaches typically involve continued pre-training on new documents.<n>Motivated by the success of the Feynman Technique in efficient human learning, we introduce Self-Tuning.
  arXiv  Detail & Related papers  (2024-06-10T14:42:20Z)
• Bilevel Continual Learning [76.50127663309604]
  We present a novel framework of continual learning named "Bilevel Continual Learning" (BCL) Our experiments on continual learning benchmarks demonstrate the efficacy of the proposed BCL compared to many state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-07-30T16:00:23Z)

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.