You Live More Than Once: Towards Hierarchical Skill Meta-Evolving

• URL: http://arxiv.org/abs/2605.28390v1
• Date: Wed, 27 May 2026 12:26:49 GMT
• Title: You Live More Than Once: Towards Hierarchical Skill Meta-Evolving
• Abstract summary: Test-time skill evolving is regarded as a new paradigm for enhancing agentic systems.<n>We show that test-time refinement of the skill evolving framework is necessary for continuous improvement of the agent systems.<n>We propose HiSME, a lightweight hierarchical skill meta-evolving solution.
• Score: 92.6633152185458
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Test-time skill evolving is regarded as a new paradigm for enhancing deployed agentic systems. Existing works mainly focus on hard-coded skill evolving strategies or parametric learning that rely on expensive parameter updates in the underlying LLMs. In this paper, we demonstrate that test-time refinement of the skill evolving framework itself is necessary for continuous improvement of the agent systems in different downstream scenarios, and lightweight algorithmic adaptation is feasible. Specifically, we propose HiSME, a lightweight hierarchical skill meta-evolving solution that jointly optimizes skills and the skill evolving strategy by learning meta-skills from agents' task execution traces. Experiments on diverse agentic benchmarks show that meta-evolving can produce a higher-quality skill library than pure skill evolving and can derive diverse meta-skills for different scenarios, thereby facilitating future continual experience learning. Our code is temporarily public at https://anonymous.4open.science/r/HiSME-BD45.

Related papers

• 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)
• SPyCE: Skill-Policy Co-evolution for Multimodal Agents [12.105041985483167]
  We propose SPyCE, a framework that distills trajectories into a hierarchical skill library and updates it throughout reinforcement learning.<n>During training, the policy model conditions on retrieved skills to guide its rollouts, while the skill library evolves using valuable rollouts generated by the policy.<n> Experiments across eight benchmarks demonstrate that SPyCE consistently outperforms both RL-based and memory-based baselines.
  arXiv  Detail & Related papers  (2026-07-15T14:01:48Z)
• MetaSkill-Evolve: Recursive Self-Improvement of LLM Agents via Two-Timescale Meta-Skill Evolution [24.78476085778134]
  Self-improving agents address this by rewriting their own skill files from execution traces, yielding meaningful gains on challenging benchmarks.<n>We introduce MetaSkill-Evolve, a two-timescale framework that makes agentic skill improvement recursive.<n>Task skills evolve on a fast loop while the meta-skill evolves on a slower one under the same pipeline applied to itself.<n>With all five pipeline agents sharing a single frozen backbone, MetaSkill-Evolve outperforms no-skill, static-skill, and single-level evolution baselines.
  arXiv  Detail & Related papers  (2026-07-06T16:40:23Z)
• Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems [16.25298848475875]
  Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks.<n>Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience.<n>Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models.<n>We propose Skill-MAS, a novel third path that decouples experience retention from parametric updates by conceptualizing the high-level orchestration capability as an evolvable Meta-Skill.
  arXiv  Detail & Related papers  (2026-06-17T09:12:50Z)
• MetaClaw: Just Talk -- An Agent That Meta-Learns and Evolves in the Wild [74.7263562191605]
  Large language model (LLM) agents are increasingly used for complex tasks.<n>Existing methods either store raw trajectories without distilling knowledge, maintain static skill libraries, or require disruptive downtime for retraining.<n>We present MetaClaw, a continual meta-learning framework that jointly evolves a base LLM policy and a library of reusable behavioral skills.
  arXiv  Detail & Related papers  (2026-03-17T22:30:30Z)
• SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning [83.98129545309277]
  We propose SkillRL, a framework that bridges the gap between raw experience and policy improvement.<n>Our approach introduces an experience-based distillation mechanism to build a hierarchical skill library SkillBank.<n> Experimental results on ALF, WebShop and seven search-augmented tasks demonstrate that SkillRL achieves state-of-the-art performance.
  arXiv  Detail & Related papers  (2026-02-09T03:17:17Z)
• Towards AGI A Pragmatic Approach Towards Self Evolving Agent [0.0]
  Large Language Model (LLM) based agents are powerful yet fundamentally static after deployment.<n>This work introduces a hierarchical self-evolving multi-agent framework that integrates a Base LLM, an operational SLM agent, a Code-Generation LLM, and a Teacher-LLM.
  arXiv  Detail & Related papers  (2026-01-15T20:43:44Z)
• Skill Expansion and Composition in Parameter Space [17.016614374151747]
  Parametric Skill Expansion and Composition (PSEC) is a new framework designed to iteratively evolve the agents' capabilities.<n>PSEC exhibits superior capacity to leverage prior knowledge to efficiently tackle new challenges.
  arXiv  Detail & Related papers  (2025-02-09T15:22:38Z)
• MetaModulation: Learning Variational Feature Hierarchies for Few-Shot Learning with Fewer Tasks [63.016244188951696]
  We propose a method for few-shot learning with fewer tasks, which is by metaulation. We modify parameters at various batch levels to increase the meta-training tasks. We also introduce learning variational feature hierarchies by incorporating the variationalulation.
  arXiv  Detail & Related papers  (2023-05-17T15:47:47Z)
• Meta-Learning Parameterized Skills [12.845774297648738]
  We propose a novel skill-learning algorithm that aims to learn transferable parameterized skills and synthesize them into a new action space. We empirically demonstrate that the proposed algorithms enable an agent to solve a set of difficult long-horizon (obstacle-course and robot manipulation) tasks.
  arXiv  Detail & Related papers  (2022-06-07T21:30:58Z)
• On the Effectiveness of Fine-tuning Versus Meta-reinforcement Learning [71.55412580325743]
  We show that multi-task pretraining with fine-tuning on new tasks performs equally as well, or better, than meta-pretraining with meta test-time adaptation. This is encouraging for future research, as multi-task pretraining tends to be simpler and computationally cheaper than meta-RL.
  arXiv  Detail & Related papers  (2022-06-07T13:24:00Z)
• Bootstrapped Meta-Learning [48.017607959109924]
  We propose an algorithm that tackles a challenging meta-optimisation problem by letting the meta-learner teach itself. The algorithm first bootstraps a target from the meta-learner, then optimises the meta-learner by minimising the distance to that target under a chosen (pseudo-)metric. We achieve a new state-of-the art for model-free agents on the Atari ALE benchmark, improve upon MAML in few-shot learning, and demonstrate how our approach opens up new possibilities.
  arXiv  Detail & Related papers  (2021-09-09T18:29:05Z)

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.