Self-evolving LLM agents with in-distribution Optimization

• URL: http://arxiv.org/abs/2606.07367v1
• Date: Fri, 05 Jun 2026 15:09:52 GMT
• Title: Self-evolving LLM agents with in-distribution Optimization
• Abstract summary: Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments.<n>We propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning.<n>We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance.
• Score: 60.05867547965365
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models (LLMs) have recently emerged as powerful controllers for interactive agents in complex environments, yet training them to perform reliable long-horizon decision making remains a fundamental challenge. A key difficulty lies in credit assignment: agents often receive delayed rewards only at the end of episodes. In this paper, we propose Q-Evolve, a self-evolving framework for LLM agents that unifies automatic process-reward labeling and policy learning within a principled in-distribution reinforcement learning paradigm. In each evolving iteration, our method learns an in-distribution critic from a hybrid off-policy dataset that combines expert demonstrations with agent-generated trajectories, stabilizing Bellman backups in sparse-reward settings via a weighted Implicit Q-Learning objective. The learned value function is then used to derive step-wise process rewards through advantage estimation, enabling dense and reliable supervision without environment backtracking or human annotation. Leveraging these signals, we perform behavior-proximal policy optimization that evolves the agent over the data used for process reward labeling, allowing iterative self-improvement without exacerbating distribution shift. We evaluate our method on AlfWorld, WebShop, and ScienceWorld, showing Q-Evolve outperforms strong baselines in sample efficiency, robustness, and overall task performance. Our results demonstrate that stable agent self-evolution is achievable through the co-evolution of process-level supervision and policy, both grounded within a shared in-distribution learning loop.

Related papers

• Teaching LLMs to Self-Evolve: Cultivating Core Meta-Skills with Reinforcement Learning [51.17262419591891]
  Test-time scaling through iterative self-evolution with environment feedback, as demonstrated by AlphaEvolve, shows remarkable performance gains.<n>We present MetaEvolve, a framework designed to develop these meta-skills via a data synthesis pipeline, evolution-aware reinforcement learning, and inference-time evolutionary search.
  arXiv  Detail & Related papers  (2026-07-24T04:35:29Z)
• SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning [38.54413500261524]
  Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but its sparse trajectory-level rewards offer limited guidance on intermediate decisions.<n>We propose SEED (SElf-Evolving On-Policy Distillation), a self-evolving framework that converts completed on-policy trajectories into training-time hindsight skills.
  arXiv  Detail & Related papers  (2026-07-16T09:57:18Z)
• SEAL: Synergistic Co-Evolution of Agents and Learning Environments [11.720414165425256]
  Large Language Model (LLM) agents are increasingly improved through interaction.<n>Most self-evolution methods adapt either the policy or the learning environment in isolation.<n>We propose SEAL, a closed-loop co-evolution framework for interactive tool-use agents.
  arXiv  Detail & Related papers  (2026-05-23T06:41:31Z)
• Utilizing and Calibrating Hindsight Process Rewards via Reinforcement with Mutual Information Self-Evaluation [50.696688705287755]
  We propose Mutual Information Self-Evaluation to overcome the sparse reward challenge in reinforcement learning.<n>MISE enables an agent to learn autonomously from dense internal rewards supplementing sparse extrinsic signals.<n>We prove that utilizing hindsight self-evaluation rewards is equivalent to minimizing an objective that combines mutual information with a KL divergence term between the policy and a proxy reward policy.
  arXiv  Detail & Related papers  (2026-04-13T15:18:51Z)
• EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle [26.048906477714937]
  Current Large Language Model (LLM) agents show strong performance in tool use, but lack the capability to systematically learn from their own experiences.<n>We introduce EvolveR, a framework designed to enable agent to self-improve through a complete, closed-loop experience lifecycle.<n>We demonstrate the effectiveness of EvolveR on complex multi-hop question-answering benchmarks, where it achieves superior performance over strong agentic baselines.
  arXiv  Detail & Related papers  (2025-10-17T12:03:16Z)
• Towards Agentic Self-Learning LLMs in Search Environment [36.158823302039195]
  We study whether self-learning can scale LLM-based agents without relying on human-curated datasets or predefined rule-based rewards.<n>We find that rewards from a Generative Reward Model (GRM) outperform rigid rule-based signals for open-domain learning.<n>We propose textbfAgentic Self-Learning (ASL), a fully closed-loop, multi-role reinforcement learning framework.
  arXiv  Detail & Related papers  (2025-10-16T03:11:56Z)
• Alignment Tipping Process: How Self-Evolution Pushes LLM Agents Off the Rails [103.05296856071931]
  We identify the Alignment Tipping Process (ATP), a critical post-deployment risk unique to self-evolving Large Language Model (LLM) agents.<n>ATP arises when continual interaction drives agents to abandon alignment constraints established during training in favor of reinforced, self-interested strategies.<n>Our experiments show that alignment benefits erode rapidly under self-evolution, with initially aligned models converging toward unaligned states.
  arXiv  Detail & Related papers  (2025-10-06T14:48:39Z)
• Agentic Reinforcement Learning with Implicit Step Rewards [92.26560379363492]
  Large language models (LLMs) are increasingly developed as autonomous agents using reinforcement learning (agentic RL)<n>We introduce implicit step rewards for agentic RL (iStar), a general credit-assignment strategy that integrates seamlessly with standard RL algorithms.<n>We evaluate our method on three challenging agent benchmarks, including WebShop and VisualSokoban, as well as open-ended social interactions with unverifiable rewards in SOTOPIA.
  arXiv  Detail & Related papers  (2025-09-23T16:15:42Z)
• Improving Retrospective Language Agents via Joint Policy Gradient Optimization [57.35348425288859]
  RetroAct is a framework that jointly optimize both task-planning and self-reflective evolution capabilities in language agents.<n>We develop a two-stage joint optimization process that integrates imitation learning and reinforcement learning.<n>We conduct extensive experiments across various testing environments, demonstrating RetroAct has substantial improvements in task performance and decision-making processes.
  arXiv  Detail & Related papers  (2025-03-03T12:54:54Z)
• 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.