8 papers
GDEPO: Group Dual-dynamic and Equal-right Advantage Policy Optimization for Sample-Efficient Reinforcement Learning
Zhengqing Yan, Xinyang Liu, Yi Zhang +7
Automated Theorem Proving (ATP) is a fundamental AI challenge, requiring machine-verifiable proofs in formal languages like Lean to evaluate reasoning. Reinforcement Learning (RL),…
DISPATCH -- Decentralized Informed Spatial Planning and Assignment of Tasks for Cooperative Heterogeneous Agents
Yao Liu, Sampad Mohanty, Elizabeth Ondula +1
Spatial task allocation in systems such as multi-robot delivery or ride-sharing requires balancing efficiency with fair service across tasks. Greedy assignment policies that match…
Ask a Strong LLM Judge when Your Reward Model is Uncertain
Zhenghao Xu, Qin Lu, Qingru Zhang +9
Reward model (RM) plays a pivotal role in reinforcement learning with human feedback (RLHF) for aligning large language models (LLMs). However, classical RMs trained on human prefe…
Optimal Aggregation of LLM and PRM Signals for Efficient Test-Time Scaling
Peng Kuang, Yanli Wang, Xiaoyu Han +3
Process reward models (PRMs) are a cornerstone of test-time scaling (TTS), designed to verify and select the best responses from large language models (LLMs). However, this promise…
Improving Sampling Efficiency in RLVR through Adaptive Rollout and Response Reuse
Yuheng Zhang, Wenlin Yao, Changlong Yu +5
Large language models (LLMs) have achieved impressive reasoning performance, with reinforcement learning with verifiable rewards (RLVR) emerging as a standard paradigm for post-tra…
The Bias is in the Details: An Assessment of Cognitive Bias in LLMs
R. Alexander Knipper, Charles S. Knipper, Kaiqi Zhang +3
As Large Language Models (LLMs) are increasingly embedded in real-world decision-making processes, it becomes crucial to examine the extent to which they exhibit cognitive biases.…
GUIDE: Towards Scalable Advising for Research Ideas
Yaowenqi Liu, Bingxu Meng, Rui Pan +4
The field of AI research is advancing at an unprecedented pace, enabling automated hypothesis generation and experimental design across diverse domains such as biology, mathematics…
Towards Large-scale Generative Ranking
Yanhua Huang, Yuqi Chen, Xiong Cao +17
Generative recommendation has recently emerged as a promising paradigm in information retrieval. However, generative ranking systems are still understudied, particularly with respe…