activity
20242026
most citedCall Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments

2 citations · 3 across the 9 of their papers we have counts for

collaborators

9 papers

cs.CL2026

RecurSE: Bounded Recursive Self-Evaluation for LLM Rubric Judges

Kaiyuan Liu, Ziyuan Zhuang, Rongxiang Weng +1

LLM-as-judge is essential for evaluating open-ended text and steering post-training, yet improving the judge itself typically relies on expensive annotations, reward models, or dis…

cs.AI2026

ACE: Pluggable Adaptive Context Elasticizer across Agents

Ning Liao, Zihao Long, Xiaoxing Wang +6

The increasing complexity of agentic tasks has led to rapidly growing trajectory lengths, which poses significant challenges for large language model (LLM) based agents with fixed…

cs.CL2026

Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation

Kaiyuan Liu, Ziyuan Zhuang, Yang Bai +3

On-policy distillation (OPD) trains a student model on its own rollouts using dense feedback from a stronger teacher. Prior literature suggests that, provided teacher feedback is a…

cs.LG2026

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization

Yang Bai, Kaiyuan Liu, Ziyuan Zhuang +5

Complex reinforcement learning environments frequently employ multi-task and mixed-reward formulations. In these settings, heterogeneous reward distributions and correlated reward…

cs.AI2025

Introducing LongCat-Flash-Thinking: A Technical Report

Meituan LongCat Team, Anchun Gui, Bei Li +122

We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a metic…

cs.CL2024★ 1 cited

EfficientRAG: Efficient Retriever for Multi-Hop Question Answering

Ziyuan Zhuang, Zhiyang Zhang, Sitao Cheng +7

Retrieval-augmented generation (RAG) methods encounter difficulties when addressing complex questions like multi-hop queries. While iterative retrieval methods improve performance…