8 papers
Dynamic Mixture of Latent Memories for Self-Evolving Agents
Dianzhi Yu, Vireo Zhang, Hongru Wang +7
Achieving self-evolution in intelligent agents requires the continual accumulation of new knowledge across changing task sequences without forgetting previously acquired abilities.…
A Survey of Audio Reasoning in Multimodal Foundation Models
Zhihan Guo, Wenqian Cui, Guan-Ting Lin +8
Reasoning has become a defining capability of modern foundation models, yet its development in the audio modality remains limited. Audio poses challenges that are distinct from tho…
Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
Bowei He, Minda Hu, Zenan Xu +7
Search-integrated reasoning enables language agents to transcend static parametric knowledge by actively querying external sources. However, training these agents via reinforcement…
ConMax: Confidence-Maximizing Compression for Efficient Chain-of-Thought Reasoning
Minda Hu, Zexuan Qiu, Zenan Xu +3
Recent breakthroughs in Large Reasoning Models (LRMs) have demonstrated that extensive Chain-of-Thought (CoT) generation is critical for enabling intricate cognitive behaviors, suc…
NILE: Internal Consistency Alignment in Large Language Models
Minda Hu, Qiyuan Zhang, Yufei Wang +7
As a crucial step to enhance LLMs alignment with human intentions, Instruction Fine-Tuning (IFT) has a high demand on dataset quality. However, existing IFT datasets often contain…
WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback
Minda Hu, Tianqing Fang, Jianshu Zhang +7
Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment…