arXiv Machine Learning

Learning Steerable Clarification Policies with Collaborative Self-play

arXiv AI
Oct 12

CLEAT: Learning Value-Guided Clarification for Interactive Agents

CLEAT (CLarification through valuE-guided Agent co-Training) is a framework that jointly trains a clarification-value controller and a task policy to improve interactive intent alignment in large language model agents. It introduces a residual query value metric, estimated via paired rollouts, to assess the utility of asking clarification questions and uses this to guide both controller predictions and policy decisions. Experiments with Qwen3-4B show CLEAT outperforming baselines across multiple benchmarks, with significant gains in user‑centric tasks and demonstrating that co‑training benefits the task policy even when the controller is omitted at inference.

By Jiatan Huang, Zheyuan Zhang, Ziming Li, Tianyi Ma, Mingchen Li, Yanfang Ye, Chuxu Zhang
Hugging Face Trending Papers
Nov 5

ReferClaw: Disambiguating User Intent for Egocentric Assistance

ReferClaw is an agentic framework designed to improve egocentric AI assistants by treating question answering as an interactive process. It uses three cooperating agents to generate candidate interpretations, ask clarifying questions, and produce answers grounded in resolved intent and visual evidence. The system balances information gain against user effort, learns from interaction, and shows higher accuracy and joint answer‑grounding performance on augmented egocentric QA benchmarks, with zero‑shot transfer across datasets.

arXiv AI
Nov 6

ReferClaw: Disambiguating User Intent for Egocentric Assistance

ReferClaw is an agentic framework designed to improve egocentric AI assistants by treating question answering as an interactive process. It uses three cooperating agents to generate candidate interpretations, ask clarifying questions, and produce answers grounded in resolved intent and visual evidence. The system balances information gain against user effort, learns from interaction, and shows better accuracy and grounding on augmented egocentric QA benchmarks, including zero‑shot transfer across datasets.

By Hangyu Qin, Junbin Xiao, Angela Yao
arXiv AI
Sep 18

UnifiedPlayers: Enhance Tool-Integrated Reasoning in Agentic Reinforcement Learning

UnifiedPlayers is a cooperative framework that jointly adapts planning, execution, and evaluation for tool-integrated reinforcement learning agents. It consists of a Planning Player that generates tasks, an Execution Player that creates multi-turn trajectories with Python tool calls, and an Evaluation Player that builds executable verifiers, all coordinated by role‑specific rewards under GRPO. The approach outperforms prior baselines on mathematical and general reasoning benchmarks and yields a verifier with high adversarial detection accuracy and more discriminative reward signals.

By Wenjie Liao, Liangjie Zhao, Zehong Cao
arXiv Computation and Language
Oct 16

Stop Training Against Soft Users: Mentalized Adversarial Self-Play for Proactive Dialogue

The paper introduces Mentalized Adversarial Self-Play (MASP), a framework for training proactive dialogue agents by modeling the user as a rationally resisting participant with an evolving mental state. MASP separates teacher and student mentalization, alternates self‑play updates for system and user policies, and treats robustness to rational resistance as a training objective. Experiments on proactive dialogue benchmarks show MASP improves success rate, rationality‑constrained success, reduces average turns, and performs better against hard users compared to SFT and Planner‑only approaches.

By Zanwu Liu, Dan Zhang, Xiaodi Wang, Yongbo Mao, Xiaoyang Guo, Yonglin Wu, Peiyue Jiang, Yangyang Wei, Zecheng Lin