Recall with Reasoning: Chain-of-Thought Distillation for Mamba's Long-Context Memory and Extrapolation

Authors: Ma, Junyu, Fang, Tianqing, Zhang, Zhisong, Zhang, Hongming, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2505.03320

WebEvolver: Enhancing Web Agent Self-Improvement with Coevolving World Model

Authors: Fang, Tianqing, Zhang, Hongming, Zhang, Zhisong, Ma, Kaixin, Yu, Wenhao, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2504.21024

Enhancing Web Agents with Explicit Rollback Mechanisms

Authors: Zhang, Zhisong, Fang, Tianqing, Ma, Kaixin, Yu, Wenhao, Zhang, Hongming, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2504.11788

DeepMath-103K: A Large-Scale, Challenging, Decontaminated, and Verifiable Mathematical Dataset for Advancing Reasoning

Authors: He, Zhiwei, Liang, Tian, Xu, Jiahao, Liu, Qiuzhi, Chen, Xingyu, Wang, Yue, Song, Linfeng, Yu, Dian, Liang, Zhenwen, Wang, Wenxuan, Zhang, Zhuosheng, Wang, Rui, Tu, Zhaopeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2504.11456

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains

Authors: Su, Yi, Yu, Dian, Song, Linfeng, Li, Juntao, Mi, Haitao, Tu, Zhaopeng, Zhang, Min, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2503.23829

Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique

Authors: Li, Yansi, Xu, Jiahao, Liang, Tian, Chen, Xingyu, He, Zhiwei, Liu, Qiuzhi, Wang, Rui, Zhang, Zhuosheng, Tu, Zhaopeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2503.17363

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Authors: Ji, Ke, Xu, Jiahao, Liang, Tian, Liu, Qiuzhi, He, Zhiwei, Chen, Xingyu, Liu, Xiaoyuan, Wang, Zhijie, Chen, Junying, Wang, Benyou, Tu, Zhaopeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2503.02875

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

Authors: Zhang, Yuheng, Yu, Dian, Ge, Tao, Song, Linfeng, Zeng, Zhichen, Mi, Haitao, Jiang, Nan, Yu, Dong

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2502.16852

Don't Get Lost in the Trees: Streamlining LLM Reasoning by Overcoming Tree Search Exploration Pitfalls

Authors: Wang, Ante, Song, Linfeng, Tian, Ye, Yu, Dian, Mi, Haitao, Duan, Xiangyu, Tu, Zhaopeng, Su, Jinsong, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2502.11183

Thoughts Are All Over the Place: On the Underthinking of o1-Like LLMs

Authors: Wang, Yue, Liu, Qiuzhi, Xu, Jiahao, Liang, Tian, Chen, Xingyu, He, Zhiwei, Song, Linfeng, Yu, Dian, Li, Juntao, Zhang, Zhuosheng, Wang, Rui, Tu, Zhaopeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2501.18585

HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Proving

Authors: Li, Yang, Du, Dong, Song, Linfeng, Li, Chen, Wang, Weikang, Yang, Tao, Mi, Haitao

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2412.20735

Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs

Authors: Chen, Xingyu, Xu, Jiahao, Liang, Tian, He, Zhiwei, Pang, Jianhui, Yu, Dian, Song, Linfeng, Liu, Qiuzhi, Zhou, Mengfei, Zhang, Zhuosheng, Wang, Rui, Tu, Zhaopeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2412.21187

Teaching LLMs to Refine with Tools

Authors: Yu, Dian, Zhang, Yuheng, Xu, Jiahao, Liang, Tian, Song, Linfeng, Tu, Zhaopeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2412.16871

Low-Bit Quantization Favors Undertrained LLMs: Scaling Laws for Quantized LLMs with 100T Training Tokens

Authors: Ouyang, Xu, Ge, Tao, Hartvigsen, Thomas, Zhang, Zhisong, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Machine Learning, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2411.17691

Towards Self-Improvement of LLMs via MCTS: Leveraging Stepwise Knowledge with Curriculum Preference Learning

Authors: Wang, Xiyao, Song, Linfeng, Tian, Ye, Yu, Dian, Peng, Baolin, Mi, Haitao, Huang, Furong, Yu, Dong

Subject Terms: Computer Science - Machine Learning, Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2410.06508

DOTS: Learning to Reason Dynamically in LLMs via Optimal Reasoning Trajectories Search

Authors: Yue, Murong, Yao, Wenlin, Mi, Haitao, Yu, Dian, Yao, Ziyu, Yu, Dong

Subject Terms: Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2410.03864

HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows

Authors: Yao, Wenlin, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence

Access URL: http://arxiv.org/abs/2409.17433

SIaM: Self-Improving Code-Assisted Mathematical Reasoning of Large Language Models

Authors: Yu, Dian, Peng, Baolin, Tian, Ye, Song, Linfeng, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Computation and Language

Access URL: http://arxiv.org/abs/2408.15565

Iterative Nash Policy Optimization: Aligning LLMs with General Preferences via No-Regret Learning

Authors: Zhang, Yuheng, Yu, Dian, Peng, Baolin, Song, Linfeng, Tian, Ye, Huo, Mingyue, Jiang, Nan, Mi, Haitao, Yu, Dong

Subject Terms: Computer Science - Machine Learning, Computer Science - Artificial Intelligence, Computer Science - Computation and Language, Computer Science - Computer Science and Game Theory

Access URL: http://arxiv.org/abs/2407.00617

LiteSearch: Efficacious Tree Search for LLM

Authors: Wang, Ante, Song, Linfeng, Tian, Ye, Peng, Baolin, Yu, Dian, Mi, Haitao, Su, Jinsong, Yu, Dong

Subject Terms: Computer Science - Computation and Language, Computer Science - Artificial Intelligence, Computer Science - Machine Learning

Access URL: http://arxiv.org/abs/2407.00320