7 papers
Attributing Structured-Output Gains in Function Calling: Interface Alignment versus Procedural Transfer
Wanyi Chen, Daoyuan Chen, Fang Kong
Structured-output benchmarks reward both task decisions and interface compliance, so prompt-induced function-calling gains require attribution before they can be interpreted as tra…
ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations
Jie Zhu, Huaixia Dou, Shuo Jiang +5
Existing emotional support conversation (ESC) systems mainly rely on end-to-end response generation or coarse strategy supervision, offering limited interpretability and little sup…
Harnesses for Inference-Time Alignment over Execution Trajectories
Boyuan Wang, Bochao Li, Minghan Wang +2
Harness engineering has emerged as an important inference-time technique for large language model (LLM) agents, aiming to improve long-term performance through task decomposition a…
Agent^2 RL-Bench: Can LLM Agents Engineer Agentic RL Post-Training?
Wanyi Chen, Xiao Yang, Xu Yang +7
We introduce Agent2 RL-Bench, a compact diagnostic benchmark for evaluating agentic RL post-training, which tests whether LLM agents can autonomously design, implement, debug, and…
SafeGen-LLM: Enhancing Safety Generalization in Task Planning for Robotic Systems
Jialiang Fan, Weizhe Xu, Mengyu Liu +3
Safety-critical task planning in robotic systems remains challenging: classical planners suffer from poor scalability, Reinforcement Learning (RL)-based methods generalize poorly,…
CARE: Cognitive-reasoning Augmented Reinforcement for Emotional Support Conversation
Jie Zhu, Yuanchen Zhou, Shuo Jiang +5
Emotional Support Conversation (ESC) plays a vital role in alleviating psychological stress and providing emotional value through dialogue. While recent studies have largely focuse…
Evaluating, Synthesizing, and Enhancing for Customer Support Conversation
Jie Zhu, Huaixia Dou, Junhui Li +4
Effective customer support requires not only accurate problem solving but also structured and empathetic communication aligned with professional standards. However, existing dialog…