From the 1 of 20 linked papers with an AI index.
7 papers · 1 filter
SkillEval: Decomposing Agent Skill Quality into Interpretable Signals
Jiahui Han, Qinuo Li, Ziheng Peng +6
Agent skills provide reusable procedural knowledge that helps agents solve specialized tasks. As their use expands, evaluating skill quality becomes increasingly important. Existin…
Recursive Synthesis for Long-Horizon Terminal Tasks
Zhongzhi Li, Yucheng Shi, Zongxia Li +8
High-quality long-horizon training data for terminal agents is expensive to produce, often costing hundreds to thousands of dollars per task, because each task must keep the instru…
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
Zongxia Li, Zhongzhi Li, Yucheng Shi +10
The paper presents Long-Horizon-Terminal-Bench, a benchmark of 46 extended tasks with fine-grained intermediate rewards to evaluate AI agents' long-horizon planning and debugging a…
TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL
Tianze Yang, Yucheng Shi, Ruitong Sun +3
Reinforcement learning (RL) for visual reasoning needs scalable, verifiable, and controllable training signals. Existing visual RL post-training trains on static curated datasets,…
MITS: Enhanced Tree Search Reasoning for LLMs via Pointwise Mutual Information
Jiaxi Li, Yucheng Shi, Xiao Huang +2
Tree search has become as a representative framework for test-time reasoning with large language models (LLMs), exemplified by methods such as Tree-of-Thought and Monte Carlo Tree…
GeoBS: Information-Theoretic Quantification of Geographic Bias in AI Models
Zhangyu Wang, Nemin Wu, Qian Cao +8
The widespread adoption of AI models, especially foundation models (FMs), has made a profound impact on numerous domains. However, it also raises significant ethical concerns, incl…