8 papers
Words to World: Benchmarking LLMs in Interactive Physical Environments
Xinnan Dai, Kaiqi Yang, Yaxin Li +9
Words are increasingly becoming an interface for action: large language models (LLMs) can now invoke tools, operate devices, and make decisions that affect the physical world. Howe…
Rep2Skill: Representation-Guided Skill Self-Evolution for LLM Agents
Kaixing Zhang, Changming Li, Yingdong Shi +5
Textual skills enable large language model (LLM) based agents to accumulate reusable procedural knowledge without updating model parameters. Yet existing skill evolution remains la…
From Static Context to Calibrated Interactive RL: Mitigating Distribution Shift in Multi-turn Dialogue with Aligned Simulator
Xiaohua Wang, Jiakang Yuan, Zisu Huang +5
A long-standing goal of the research community is to develop highly interactive LLM-based dialogue agents. Recent research focuses on optimizing policies based on fixed offline log…
Foresight Optimization for Strategic Reasoning in Large Language Models
Jiashuo Wang, Jiawen Duan, Jian Wang +6
Reasoning capabilities in large language models (LLMs) have generally advanced significantly. However, it is still challenging for existing reasoning-based LLMs to perform effectiv…
UI-Copilot: Advancing Long-Horizon GUI Automation via Tool-Integrated Policy Optimization
Zhengxi Lu, Fei Tang, Guangyi Liu +8
MLLM-based GUI agents have demonstrated strong capabilities in complex user interface interaction tasks. However, long-horizon scenarios remain challenging, as these agents are bur…
Reward Hacking in the Era of Large Models: Mechanisms, Emergent Misalignment, Challenges
Xiaohua Wang, Muzhao Tian, Yuqi Zeng +20
Reinforcement Learning from Human Feedback (RLHF) and related alignment paradigms have become central to steering large language models (LLMs) and multimodal large language models…
From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient
Changming Li, Kaixing Zhang, Haoyun Xu +4
Large Language Models (LLMs) demonstrate remarkable reasoning capabilities, yet the internal mechanisms driving these multi-step processes remain opaque. Existing mechanistic inter…
Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
Zheng Zhang, Ziwei Shan, Kaitao Song +2
Process Reward Models (PRMs) have emerged as a promising approach to enhance the reasoning capabilities of large language models (LLMs) by guiding their step-by-step reasoning towa…