10 papers
EGCForest: Structured Agent Memory Organization for Enterprise Group Chats
Lingxi Cui, Jinhao Ruan, Wenqing Wei +4
Enterprise group chats record project progress, decisions, task ownership, and other organizational information valuable to enterprise agents. Reliable retrieval is challenging bec…
Gödel Forest: Balancing Search Depth and Breadth for Data-Centric Recursive Self-Improvement
Ziqi Zhao, Fanqing Meng, Haocheng Lu +4
Recursive self-improvement (RSI) aims to achieve compounding gains by having models improve themselves. While most existing RSI systems optimize external agent harnesses or prompts…
AI Can Learn Scientific Taste
Jingqi Tong, Mingzhe Li, Hangcheng Li +20
Scientific discovery depends on expert judgement and foresight, which we call scientific taste: the ability to judge and propose research ideas with the potential for long-term sci…
The Universal Landscape of Human Reasoning
Qiguang Chen, Jinhao Liu, Libo Qin +14
Understanding how information is dynamically accumulated and transformed in human reasoning has long challenged cognitive psychology, philosophy, and artificial intelligence. Exist…
Can LLMs Refuse Questions They Do Not Know? Measuring Knowledge-Aware Refusal in Factual Tasks
Wenbo Pan, Jie Xu, Qiguang Chen +5
Large Language Models (LLMs) should refuse to answer questions beyond their knowledge. This capability, which we term knowledge-aware refusal, is crucial for factual reliability, w…
CCHall: A Novel Benchmark for Joint Cross-Lingual and Cross-Modal Hallucinations Detection in Large Language Models
Yongheng Zhang, Xu Liu, Ruoxi Zhou +4
Investigating hallucination issues in large language models (LLMs) within cross-lingual and cross-modal scenarios can greatly advance the large-scale deployment in real-world appli…
RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning
Qiguang Chen, Libo Qin, Jinhao Liu +4
Chain-of-Thought (CoT) reasoning has proven effective in enhancing large language models (LLMs) on complex tasks, spurring research into its underlying mechanisms. However, two pri…
DLPO: Towards a Robust, Efficient, and Generalizable Prompt Optimization Framework from a Deep-Learning Perspective
Dengyun Peng, Yuhang Zhou, Qiguang Chen +3
Large Language Models (LLMs) have achieved remarkable success across diverse tasks, largely driven by well-designed prompts. However, crafting and selecting such prompts often requ…
DivIL: Unveiling and Addressing Over-Invariance for Out-of- Distribution Generalization
Jiaqi Wang, Yuhang Zhou, Zhixiong Zhang +3
Out-of-distribution generalization is a common problem that expects the model to perform well in the different distributions even far from the train data. A popular approach to add…
Wrong-of-Thought: An Integrated Reasoning Framework with Multi-Perspective Verification and Wrong Information
Yongheng Zhang, Qiguang Chen, Jingxuan Zhou +5
Chain-of-Thought (CoT) has become a vital technique for enhancing the performance of Large Language Models (LLMs), attracting increasing attention from researchers. One stream of a…