analiza aiqbench
This paper introduces AdvRole, a closed-loop reinforcement learning framework that dynamically evolves training scenarios to address distributional bottlenecks in role-playing agents. By employing an adversarial rewriter to generate specific hard examples, the method ensures continuous improvement across under-mastered regions of the character-context space. The approach demonstrates significant performance gains on multilingual benchmarks, advancing the state-of-the-art for adaptive LLM-based social simulations.
Adversarial Closed-Loop Curriculum for Evolving Role-Playing Agents
arXiv:2609.28609v1 Announce Type: new Abstract: Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL methods typically train on a fixed scenario pool collected before learning begins. This creates a distributional bottleneck: as the agent improves, the scenarios where it performs poorly also change, while the training distribution remains static. Therefore, we propose AdvRole, an adversarial context rewriting framework that turns role-playing RL into a closed-loop curriculum. AdvRole alternates between an Actor that learns to role-play and a Rewriter that edits character profiles and dialogue contexts into actor-specific hard scenarios. The Rewriter is trained with a performance-gap reward, which favors rewrites that reduce the current Actor's score relative to the original scenario. As a result, the scenario pool evolves with the Actor and continuously targets under-mastered regions of the character-context space. Experiments on three role-playing benchmarks covering English and Chinese, as well as a new multilingual benchmark we release, show that AdvRole consistently outperforms baselines.
Abstract:Role-playing agents based on large language models have been widely applied in areas such as personalized assistance and social simulation. Recent RL methods typically train on a fixed scenario pool collected before learning begins. This creates a distributional bottleneck: as the agent improves, the scenarios where it performs poorly also change, while the training distribution remains static. Therefore, we propose AdvRole, an adversarial context rewriting framework that turns role-playing RL into a closed-loop curriculum. AdvRole alternates between an Actor that learns to role-play and a Rewriter that edits character profiles and dialogue contexts into actor-specific hard scenarios. The Rewriter is trained with a performance-gap reward, which favors rewrites that reduce the current Actor's score relative to the original scenario. As a result, the scenario pool evolves with the Actor and continuously targets under-mastered regions of the character-context space. Experiments on three role-playing benchmarks covering English and Chinese, as well as a new multilingual benchmark we release, show that AdvRole consistently outperforms baselines.
Artificial Intelligence (cs.AI)
arXiv:2609.28609 [cs.AI]
(or arXiv:2609.28609v1 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2609.28609 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 254 cuvinte
Subiecte conexe
Assessing Information Ecosystems : How Governments Can Get Ahead of Hybrid Threats
carnegieendowment.org · 5 aug. 2026
Building trust in AI agents: A production-ready evaluation framework with Amazon Bedrock AgentCore
AWS · 16 oct. 2026
Debating RSI, the US-China Gap, and Jaggedness with JS Denain of Epoch AI
Interconnects · 22 sept. 2026
[AINews] Reality Checks on AI News (Yegge shuts down Gas Town, Databricks’ +60% Astra cost)
Latent Space · 17 sept. 2026