1 citations · 1 across the 9 of their papers we have counts for
8 papers · 1 filter
ReTerm: Recovery Training for Self-Improving Terminal Agents
Wei Xie, Kaituo Feng, Shiming Fu +3
Terminal agents have shown strong abilities in complex coding tasks. However, they often struggle to recover from errors during long-running execution (e.g., command errors, faulty…
Discovering Diverse Planning Policies for Multimodal Embodied Agents with Quality-Diversity Optimization
Pengfei Xu, Yong Liu, Xiaoya Nan +2
Multimodal embodied agents are increasingly required to solve long-horizon tasks by integrating visual observations, textual goals, and interaction history into closed-loop decisio…
Structure-Conditioned Actor-Critic Branches for Quality-Diversity Reinforcement Learning
Lianrong Zuo, Peilan Xu, Yong Liu +1
Quality-diversity reinforcement learning (QD-RL) aims to construct policy repertoires that contain both high-performing and behaviorally diverse policies. Existing QD-RL methods ma…
Statistical Priors for Implicit Preferences: Decoupling Skill Selection as a Local Harness in Personal Agents
Zeyu Gan, Huayi Tang, Yong Liu
As Large Language Model (LLM) capabilities advance, locally deployed personal agents relying on API-based remote models and external skills have emerged as a novel paradigm. With t…
Capabilities and Fundamental Limits of Latent Chain-of-Thought
Jiaxuan Zou, Yaozhong Xiong, Yong Liu
Latent Chain-of-Thought (Latent CoT) models promise efficient reasoning via continuous representations, yet exhibit puzzling performance inconsistencies: excelling at exploration (…
Why Does Reasoning Length Converge? Unveiling the Underfitting-Overfitting Trade-off in Chain-of-Thought
Zeyu Gan, Hao Yi, Yong Liu
Test-time scaling, primarily manifested through multi-step Chain-of-Thought (CoT) reasoning via Reinforcement Learning (RL), has emerged as a pivotal paradigm for enhancing the rea…
Rethinking External Slow-Thinking: From Snowball Errors to Probability of Correct Reasoning
Zeyu Gan, Yun Liao, Yong Liu
Test-time scaling, which is also often referred to as slow-thinking, has been demonstrated to enhance multi-step reasoning in large language models (LLMs). However, despite its wid…
Towards a Theoretical Understanding of Synthetic Data in LLM Post-Training: A Reverse-Bottleneck Perspective
Zeyu Gan, Yong Liu
Synthetic data has become a pivotal resource in post-training tasks for large language models (LLMs) due to the scarcity of high-quality, specific data. While various methods have…