Related papers: Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution

Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution

URL: http://arxiv.org/abs/2606.10917v1
Date: Tue, 09 Jun 2026 14:28:07 GMT
Title: Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Abstract summary: Role-Agent harnesses a single Large Language Model (LLM) to function concurrently as both the agent and the environment.<n>Role-Agent consistently improves performance, yielding an average gain of over 4% over strong baselines.
Score: 25.26084224278813
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static training environments, which hinder broader generalization. To address these limitations, this paper introduces Role-Agent, \textcolor{black}{a framework} that harnesses a single LLM to function concurrently as both the agent and the environment, enabling a bootstrapped co-evolution. Role-Agent comprises two synergistic components: World-In-Agent (WIA) and Agent-In-World (AIW). In WIA, the LLM acts as the agent and predicts future states after each action; the alignment between predicted and actual states is then used as a process reward, encouraging environment-aware reasoning. In AIW, the LLM analyzes failure modes from failed trajectories and retrieves tasks with similar failure patterns, thereby reshaping the training data distribution for targeted practice. Experiments on multiple benchmarks show that Role-Agent consistently improves performance, yielding an average gain of over 4\% over strong baselines.

Related papers

DLLM Agent: See Farther, Run Faster [94.74432470237817]
Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
arXiv Detail & Related papers (2026-02-07T09:01:18Z)
Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement [61.35824395228412]
Large language model (LLM) based agents are increasingly used to tackle software engineering tasks.<n>We propose Self-Abstraction from Grounded Experience (SAGE), a framework that enables agents to learn from their own task executions.
arXiv Detail & Related papers (2025-11-08T08:49:38Z)
Grounded Test-Time Adaptation for LLM Agents [75.62784644919803]
Large language model (LLM)-based agents struggle to generalize to novel and complex environments.<n>We propose two strategies for adapting LLM agents by leveraging environment-specific information available during deployment.
arXiv Detail & Related papers (2025-11-06T22:24:35Z)
Multi-Agent Tool-Integrated Policy Optimization [67.12841355267678]
Large language models (LLMs) increasingly rely on multi-turn tool-integrated planning for knowledge-intensive and complex reasoning tasks.<n>Existing implementations typically rely on a single agent, but they suffer from limited context length and noisy tool responses.<n>No existing methods support effective reinforcement learning post-training of tool-integrated multi-agent frameworks.
arXiv Detail & Related papers (2025-10-06T10:44:04Z)
Agentic Reinforced Policy Optimization [66.96989268893932]
Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
arXiv Detail & Related papers (2025-07-26T07:53:11Z)
Multiple Weaks Win Single Strong: Large Language Models Ensemble Weak Reinforcement Learning Agents into a Supreme One [28.264011412168347]
Model ensemble is a useful approach in reinforcement learning (RL) for training effective agents.<n>We propose LLM-Ens, a novel approach that enhances RL model ensemble with task-specific semantic understandings.
arXiv Detail & Related papers (2025-05-21T09:35:43Z)
Advancing Language Multi-Agent Learning with Credit Re-Assignment for Interactive Environment Generalization [38.68388721203677]
We propose CollabUIAgents, a multi-agent reinforcement learning framework with a novel multi-agent credit re-assignment strategy.<n>We show that our framework improves both performance and cross-environment generalizability of multi-agent systems.
arXiv Detail & Related papers (2025-02-20T12:26:15Z)
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)
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning [13.753960633998389]
Reinforcement learning (RL) has emerged as a pivotal technique for fine-tuning large language models (LLMs) on specific tasks.<n>In this paper, we propose CORY, extending the RL fine-tuning of LLMs to a sequential cooperative multi-agent reinforcement learning framework.<n>Results show that CORY outperforms PPO in terms of policy optimality, resistance to distribution collapse, and training robustness.
arXiv Detail & Related papers (2024-10-08T14:55:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.