Entity · paper

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

paperactiverole-agent-bootstrapping-llm-agents-via-dual-role-evolution-699acb70·1 events·first seen Jun 10, 2026

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

Co-occurring entities

More like this (12)

Multi-Component LLM Agent Generative Skill Composition for LLM Agents From Atomic Actions to Standard Operating Procedures: Iterative Tool Optimization for Self-Evolving LLM Agents Model-Generated Agent Skills (paper)What LLM Agents Say When No One Is Watching: Social Structure and Latent Objective Emergence in Multi-Agent Debates Multi-Agent Fictitious Play Always-OnAgents: A Survey of Persistent Memory, State, and Governance in LLM Agents Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills Progress Advantage for LLM Agents Dynamic Verifiable Multi-Agent Human Agentic Loyalty Loop Reward Modeling for Multi-Agent Orchestration Agentopia: Long-Term Life Simulation and Learning in Agent Societies

Recent events (1)

5arXiv · cs.AI·Jun 10, 2026·source ↗

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

Role-Agent is a new framework that uses a single LLM simultaneously as both agent and environment, enabling self-bootstrapped co-evolution without external environment feedback. The system has two components: World-In-Agent (WIA), which uses predicted vs. actual state alignment as a process reward, and Agent-In-World (AIW), which reshapes training data by retrieving tasks with similar failure patterns. Experiments across multiple benchmarks show an average performance gain of over 4% over strong baselines. The approach addresses key limitations in LLM agent training: inefficient feedback and static environments.

Agent and Tool Ecosystem Alignment and RLHF Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution World-In-Agent