11 papers
Retrospective Progress-Aware Self-Refinement for LLM Agent Training
Xinbei Ma, Congmin Zheng, Jiyang Qiu +10
LLM-based agents trained with reinforcement learning optimize step-wise action prediction but lack metacognitive awareness of task progress, inducing a gap that hinders long-horizo…
CoLD: Counterfactually-Guided Length Debiasing for Process Reward Models in Mathematical Reasoning
Congmin Zheng, Jiachen Zhu, Jianghao Lin +6
Process Reward Models (PRMs) play a central role in evaluating and guiding multi-step reasoning in large language models (LLMs), especially for mathematical problem solving. Howeve…
Contexting as Recommendation: Evolutionary Collaborative Filtering for Context Engineering
Jiachen Zhu, Zhuoying Ou, Congmin Zheng +9
Large Language Models (LLMs) are highly sensitive to their input contexts, motivating the development of automated context engineering. However, existing methods predominantly trea…
A Survey of Process Reward Models: From Outcome Signals to Process Supervisions for Large Language Models
Congmin Zheng, Jiachen Zhu, Zhuoying Ou +8
Although Large Language Models (LLMs) exhibit advanced reasoning ability, conventional alignment remains largely dominated by outcome reward models (ORMs) that judge only final ans…
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Chenyu Zhou, Huacan Chai, Wenteng Chen +18
Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the…
Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization
Jiachen Zhu, Lingyu Yang, Rong Shan +6
The rise of autonomous GUI agents has triggered adversarial countermeasures from digital platforms, yet existing research prioritizes utility and robustness over the critical dimen…