Almanac
paper

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

paperactiveprovisionalrole-agent-bootstrapping-llm-agents-via-dual-role-evolution-699acb70·1 events·first seen 7d ago

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

Co-occurring entities

More like this (12)

Recent events (1)

5arXiv · cs.AI·7d ago·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.