activity
20242026
collaborators

7 papers

cs.LG2026

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Kewei Xu, Xiaoben Lu, Shuofei Qiao +4

Real-world data analysis is inherently iterative, yet existing benchmarks mostly evaluate isolated or short interactive tasks, leaving agents' ability to track evolving analytical…

cs.CL2026

LightThinker++: From Reasoning Compression to Memory Management

Yuqi Zhu, Jintian Zhang, Zhenjie Wan +7

Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces. In this paper, we propose LightTh…

cs.LG2026

Sparse-RL: Breaking the Memory Wall in LLM Reinforcement Learning via Stable Sparse Rollouts

Sijia Luo, Xiaokang Zhang, Yuxuan Hu +6

Reinforcement Learning (RL) has become essential for eliciting complex reasoning capabilities in Large Language Models (LLMs). However, the substantial memory overhead of storing K…

cs.CL2025

LookAhead Tuning: Safer Language Models via Partial Answer Previews

Kangwei Liu, Mengru Wang, Yujie Luo +7

Fine-tuning enables large language models (LLMs) to adapt to specific domains, but often compromises their previously established safety alignment. To mitigate the degradation of m…

cs.CL2025

KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents

Yuqi Zhu, Shuofei Qiao, Yixin Ou +7

Large Language Models (LLMs) have demonstrated great potential in complex reasoning tasks, yet they fall short when tackling more sophisticated challenges, especially when interact…

cs.CL2025

OneKE: A Dockerized Schema-Guided LLM Agent-based Knowledge Extraction System

Yujie Luo, Xiangyuan Ru, Kangwei Liu +10

We introduce OneKE, a dockerized schema-guided knowledge extraction system, which can extract knowledge from the Web and raw PDF Books, and support various domains (science, news,…