9 papers
Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-Verification
Yingfeng Luo, Shaowei Wei, Daixin Wang +7
Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments. Yet how trustworthy such sel…
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
Xinyu Lu, Tianshu Wang, Pengbo Wang +8
Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next-level capability: whether m…
Evaluating Interactive Reasoning in Large Language Models: A Hierarchical Benchmark with Executable Games
Mingyuan Fan, Weiguang Han, Daixin Wang +3
We introduce a multi-turn interactive framework for reasoning evaluation that treats reasoning as active evidence acquisition and belief updating. Wherein, LLMs receive only the ta…
When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
Mingyuan Fan, Weiguang Han, Daixin Wang +3
Reinforcement Learning with Verifiable Rewards (RLVR) is a central paradigm for turning large language models (LLMs) into reliable problem solvers, especially in logic-heavy domain…
HiMA-Ecom: A Long-Horizon Memory Benchmark for Hierarchical Multi-Agent E-commerce Assistants
Junxing Hu, Ai Han, Haolan Zhan +8
Long-horizon agentic systems become long-context systems by accumulation rather than through a single long document, since every step reassembles a prompt from role instructions, t…
SHARP: Synthesizing High-quality Aligned Reasoning Problems for Large Reasoning Models Reinforcement Learning
Xiong Jun Wu, Zhenduo Zhang, ZuJie Wen +11
Training large reasoning models (LRMs) with reinforcement learning in STEM domains is hindered by the scarcity of high-quality, diverse, and verifiable problem sets. Existing synth…
MASS: Mathematical Data Selection via Skill Graphs for Pretraining Large Language Models
Jiazheng Li, Lu Yu, Qing Cui +4
High-quality data plays a critical role in the pretraining and fine-tuning of large language models (LLMs), even determining their performance ceiling to some degree. Consequently,…
IceBerg: Debiased Self-Training for Class-Imbalanced Node Classification
Zhixun Li, Dingshuo Chen, Tong Zhao +5
Graph Neural Networks (GNNs) have achieved great success in dealing with non-Euclidean graph-structured data and have been widely deployed in many real-world applications. However,…
Mix Data or Merge Models? Balancing the Helpfulness, Honesty, and Harmlessness of Large Language Model via Model Merging
Jinluan Yang, Dingnan Jin, Anke Tang +10
Achieving balanced alignment of large language models (LLMs) in terms of Helpfulness, Honesty, and Harmlessness (3H optimization) constitutes a cornerstone of responsible AI. Exist…