Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems

• URL: http://arxiv.org/abs/2606.18837v2
• Date: Wed, 24 Jun 2026 05:57:28 GMT
• Title: Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems
• Abstract summary: 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.
• Score: 16.25298848475875
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large Language Model (LLM)-based automatic Multi-Agent Systems (MAS) generation has become a crucial frontier for tackling complex tasks. However, existing methods face a dilemma between model capability and experience retention. Inference-time MAS leverages frozen frontier LLMs but repeats identical searches without learning from past experience. Conversely, Training-time MAS internalizes experience via gradient updates but is constrained by the low capability ceiling of smaller models, and is hard to scale to large frontier LLMs. To bridge this gap, 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. Skill-MAS refines this architectural knowledge through a closed optimization loop: (1) Multi-Trajectory Rollout samples a behavioral distribution for each task under the current Meta-Skill; and (2) Selective Reflection adaptively selects priority tasks and applies hierarchical contrastive analysis to distill systemic experience into generalizable, strategy-level principles. Extensive experiments across four complex benchmarks and four distinct LLMs demonstrate that Skill-MAS not only achieves remarkable performance gains but also maintains a favorable cost-performance trade-off. Further analysis reveals that the evolved Meta-Skills are highly robust and exhibit strong transferability across unseen tasks and different LLMs.

Related papers

• Skill is Not One-Size-Fits-All: Model-Aware Skill Alignment for LLM Agents [9.144810798419975]
  LLM agents increasingly retrieve externally curated skills-procedural instructions retrieved at decision time to improve performance on long-horizon interactive tasks.<n>We propose MASA Model-Aware Skill Alignment, a framework that adapts skills to each target backbone without modifying agent weights.<n> MASA consistently achieves the best overall performance, with gains of up to 25.8 points over the strongest baseline.
  arXiv  Detail & Related papers  (2026-05-29T01:34:42Z)
• Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters [56.051481747681315]
  Cross-modal skill injection aims to induce emergent cross-modal capabilities by integrating a domain-expert LLM into a Vision-Language Models (VLMs)<n>For scenarios, we find that cross-modal skill injection generally performs well in instruction-following and cross-lingual settings, yet struggles with mathematical reasoning.<n>For methods, we find that classic approaches such as TA and DARE consistently achieve superior performance over alternative merging methods.
  arXiv  Detail & Related papers  (2026-05-19T08:24:19Z)
• FutureMind: Equipping Small Language Models with Strategic Thinking-Pattern Priors via Adaptive Knowledge Distillation [13.855534865501369]
  Small Language Models (SLMs) are attractive for cost-sensitive and resource-limited settings due to their efficient, low-latency inference.<n>We propose FutureMind, a modular reasoning framework that equips SLMs with strategic thinking-pattern priors.
  arXiv  Detail & Related papers  (2026-02-01T13:26:04Z)
• MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization [103.74675519953898]
  Long-chain reflective reasoning is a prerequisite for solving complex real-world problems.<n>We build a benchmark consisting 1,260 samples of 42 challenging synthetic tasks.<n>We generate post-training data and explore learning paradigms for exploiting such data.
  arXiv  Detail & Related papers  (2025-10-09T17:53:58Z)
• Learning on the Job: An Experience-Driven Self-Evolving Agent for Long-Horizon Tasks [42.78572295558531]
  Large Language Models have demonstrated remarkable capabilities across diverse domains, yet significant challenges persist when deploying them as AI agents for real-world long-horizon tasks.<n>Existing LLM agents suffer from a critical limitation: they are test-time static and cannot learn from experience, lacking the ability to accumulate knowledge and continuously improve on the job.<n>We propose MUSE, a novel agent framework that introduces an experience-driven, self-evolving system centered around a hierarchical Memory Module.
  arXiv  Detail & Related papers  (2025-10-09T09:40:34Z)
• MARS: Optimizing Dual-System Deep Research via Multi-Agent Reinforcement Learning [82.14973479594367]
  Large Language Models (LLMs) for complex reasoning tasks require innovative approaches that bridge intuitive and deliberate cognitive processes.<n>This paper introduces a Multi-Agent System for Deep ReSearch (MARS) enabling seamless integration of System 1's fast, intuitive thinking with System 2's deliberate reasoning.
  arXiv  Detail & Related papers  (2025-10-06T15:42:55Z)
• MCCE: A Framework for Multi-LLM Collaborative Co-Evolution [17.41200156551317]
  Multi-objective discrete optimization problems pose significant challenges due to their vast and unstructured spaces.<n>Large language models (LLMs) offer powerful priors and reasoning ability, making them naturals when expert knowledge matters.<n>We introduce Multi-LLM Collaborative Co-evolution, a hybrid framework that unites a frozen closed-source LLM with a lightweight trainable model.
  arXiv  Detail & Related papers  (2025-10-06T10:03:28Z)
• RLAE: Reinforcement Learning-Assisted Ensemble for LLMs [21.77261258691006]
  Large language models (LLMs) can effectively combine diverse strengths of different models, offering a promising approach to enhance performance across various tasks.<n>We propose Reinforcement Learning-Assisted Ensemble for LLMs, a novel framework that reformulates ensemble through the lens of a Markov Decision Process (MDP)<n>Our approach introduces a RL agent that dynamically adjusts ensemble weights by considering both input context and intermediate generation states.
  arXiv  Detail & Related papers  (2025-05-31T07:38:41Z)
• ReMA: Learning to Meta-think for LLMs with Multi-Agent Reinforcement Learning [53.817538122688944]
  We introduce Reinforced Meta-thinking Agents (ReMA) to elicit meta-thinking behaviors from Reasoning of Large Language Models (LLMs)<n>ReMA decouples the reasoning process into two hierarchical agents: a high-level meta-thinking agent responsible for generating strategic oversight and plans, and a low-level reasoning agent for detailed executions.<n> Empirical results from single-turn experiments demonstrate that ReMA outperforms single-agent RL baselines on complex reasoning tasks.
  arXiv  Detail & Related papers  (2025-03-12T16:05:31Z)
• Satori: Reinforcement Learning with Chain-of-Action-Thought Enhances LLM Reasoning via Autoregressive Search [57.28671084993782]
  Large language models (LLMs) have demonstrated remarkable reasoning capabilities across diverse domains.<n>Recent studies have shown that increasing test-time computation enhances LLMs' reasoning capabilities.<n>We propose a two-stage training paradigm: 1) a small-scale format tuning stage to internalize the COAT reasoning format and 2) a large-scale self-improvement stage leveraging reinforcement learning.
  arXiv  Detail & Related papers  (2025-02-04T17:26:58Z)
• MALT: Improving Reasoning with Multi-Agent LLM Training [67.76186488361685]
  MALT (Multi-Agent LLM Training) is a novel post-training strategy that divides the reasoning process into generation, verification, and refinement steps.<n>On MATH, GSM8K, and CSQA, MALT surpasses the same baseline LLM with a relative improvement of 15.66%, 7.42%, and 9.40% respectively.
  arXiv  Detail & Related papers  (2024-12-02T19:30:36Z)
• Weakly Supervised Temporal Action Localization via Dual-Prior Collaborative Learning Guided by Multimodal Large Language Models [33.37379526356273]
  We introduce a novel learning paradigm termed MLLM4WTAL.<n>It harnesses the potential of MLLM to offer temporal action key semantics and complete semantic priors.<n>It achieves this by integrating two distinct modules: Key Semantic Matching (KSM) and Complete Semantic Reconstruction (CSR)
  arXiv  Detail & Related papers  (2024-11-13T09:37:24Z)
• From Novice to Expert: LLM Agent Policy Optimization via Step-wise Reinforcement Learning [62.54484062185869]
  We introduce StepAgent, which utilizes step-wise reward to optimize the agent's reinforcement learning process.<n>We propose implicit-reward and inverse reinforcement learning techniques to facilitate agent reflection and policy adjustment.
  arXiv  Detail & Related papers  (2024-11-06T10:35:11Z)

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.