6arXiv cs.CL (Computation and Language)·
MetaEvolve framework trains LLMs to self-evolve via meta-skill reinforcement learning
Researchers introduce MetaEvolve, a framework that cultivates 'meta-skills' such as self-reflection and multi-round refinement in LLMs through a data synthesis pipeline and evolution-aware reinforcement learning. Grounded in coding tasks where program execution provides continuous reward signals, the system trains on evolution trajectories containing programs, fitness scores, and attempt histories. MetaEvolve outperforms the strongest baseline by 10.01% on in-distribution coding benchmarks and 24.12% on out-of-distribution tasks, with a 46.9% relative improvement on open-ended algorithm optimization problems outside the training domain. The work is motivated by AlphaEvolve-style test-time scaling and aims to produce generalizable meta-skills transferable to domains with sparse training signals.
Related guides (3)
Related events (8)
MLEvolve: Self-evolving multi-agent framework for automated ML algorithm discovery
MLEvolve is a new LLM-based multi-agent framework for end-to-end machine learning algorithm discovery, addressing limitations of existing MLE agents including information isolation and memoryless search. The system introduces Progressive MCGS (a graph-extended tree search), Retrospective Memory for experience accumulation, and decoupled strategic planning from code generation. Evaluated on MLE-Bench, it achieves state-of-the-art medal and valid submission rates within a 12-hour budget, and also outperforms AlphaEvolve on mathematical algorithm optimization tasks.
Skill Self-Play: Co-evolving LLM capabilities via structured self-play with dynamic skill routing
Researchers introduce Skill Self-Play (Skill-SP), a reinforcement learning framework that addresses the diversity-vs-verifiability dilemma in LLM self-evolution by using agent skills as a middle ground. The system comprises a proposer, solver, and dynamic skill controller that co-evolve in a continuous loop: the proposer generates tasks conditioned on sampled skills, the solver explores solutions, and the skill controller updates an expanding skill library based on execution feedback. Evaluations on tool-use and reasoning benchmarks show consistent performance gains on capable backbones and recovery for initially misaligned models. Code is released under the Qwen-Applications GitHub organization, suggesting Alibaba/Qwen team involvement.
Double Ratchet: Co-evolving evaluation metrics and skills for self-improving LLM agents
A new arXiv preprint introduces Double Ratchet, a system that co-evolves both evaluation metrics and agent skills in settings where no reliable automatic verifier exists. The metric loop uses evolutionary search over small drawback detectors anchored to a small reference set, while the skill loop uses a lifecycle-managed approach; together they retain 88–110% of the performance lift achievable with ground-truth metrics across code generation (MBPP+), text-to-SQL (Spider 2.0-Snow), and report generation tasks. The paper also addresses safety, showing that anchor discipline and outer audits can catch and repair cases where evolved skills game the rubric. This work directly addresses a core bottleneck in self-improving agent systems: the chicken-and-egg problem of needing a reliable evaluator to improve.
Evolved Policy Gradients: OpenAI Meta-Learning via Loss Function Evolution
OpenAI released Evolved Policy Gradients (EPG), a meta-learning method that evolves the loss function used to train reinforcement learning agents rather than hand-designing it. The approach enables faster adaptation to novel tasks, with agents demonstrating generalization to test-time scenarios outside their training distribution, such as navigating to objects placed in new locations. EPG represents an experimental direction in automated algorithm discovery for RL.
AutoMem: Automated framework trains LLMs to manage memory as a learnable cognitive skill
AutoMem is a new framework that treats memory management in LLMs as a trainable skill, using two optimization loops: one that iteratively revises memory structure via trajectory review by a strong LLM, and one that distills good memory decisions into direct training signal for the agent model. Evaluated on three long-horizon procedurally generated games (Crafter, MiniHack, NetHack), optimizing memory alone yielded 2x-4x performance improvements, bringing a 32B open-weight model competitive with frontier systems like Claude Opus 4.5 and Gemini 3.1 Pro Thinking. The work draws on cognitive science concepts of metamemory and demonstrates that memory management is an independently learnable, high-leverage capability for long-horizon agentic tasks.
EvoSOP: LLM agents self-evolve by synthesizing atomic actions into reusable Standard Operating Procedures
Researchers propose EvoSOP, a framework enabling LLM agents to extract reusable Standard Operating Procedures (SOPs) from execution trajectories, effectively converting sequences of atomic tool calls into higher-order callable tools. The framework iteratively optimizes the agent's toolset through a lifecycle of construction, merging, evaluation, and pruning. Experiments show EvoSOP improves task success rates and reduces interaction rounds compared to static-toolset baselines, offering a scalable path toward self-evolving agents.
LLM-guided MAP-Elites evolution improves medical decision pipelines at inference time
Researchers propose using LLM-guided MAP-Elites evolutionary search as an inference-time alternative to fine-tuning for adapting LLMs to clinical workflows, formulating triage, consultation, and image classification as evolutionary searches over executable artifacts. Across three medical settings, evolved programs substantially outperform manually designed baselines: triage accuracy improves from 77.3% to 87.1% and emergency recall from 0.60 to 0.97, with gains also shown on MIMIC-ESI, iCRAFTMD, and PneumoniaMNIST. The approach works across Llama-3, Qwen-3.5, and Gemma-4 backbones and produces interpretable program-level mechanisms rather than superficial prompt changes.
Reinforcement Learning with Metacognitive Feedback (RLMF) improves LLM calibration and uncertainty expression
Researchers introduce Reinforcement Learning with Metacognitive Feedback (RLMF), a training paradigm that refines preference optimization using a model's self-judgments of its own performance quality. The method is applied to faithful calibration — aligning a model's expressed confidence with its intrinsic uncertainty — and achieves state-of-the-art results across diverse tasks while outperforming standard RL by up to 63%. A companion technique, metacognitive data selection, uses similar self-judgments to identify high-value training examples, outperforming naive active learning baselines. The work positions metacognitive performance as a novel and effective RL signal for improving LLM reliability and alignment.