7 papers
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…
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…
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…
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…
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…
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,…