Published in ICLR 2025, 2025
本文提出了一种新的Agent微调方法AgentRefine，通过细化调整来增强Agent的泛化能力。
Recommended citation: Fu, D., He, K., Wang, Y., Hong, W., Gongque, Z., Zeng, W., Wang, W., Wang, J., Cai, X., & Xu, W. (2025). AgentRefine: Enhancing Agent Generalization through Refinement Tuning. In International Conference on Learning Representations (ICLR 2025).
Download Paper
Published in EMNLP 2024, 2024
本文提出了一种多尺度洞察的具身智能体MSI-Agent，用于提升规划和决策能力。
Recommended citation: Fu, D., Qi, B., Gao, Y., Jiang, C., Dong, G., & Zhou, B. (2024). MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
Download Paper
Published in EMNLP 2024, 2024
本文探讨了如何通过高质量数据来增强代码语言模型的指令调优。
Recommended citation: Wang, Y.*, He, K.*, Fu, D.*, Gongque, Z., Xu, H., Chen, Y., Wang, Z., Fu, Y., Dong, G., Diao, M., Wang, J., Zhang, M., Cai, X., & Xu, W. (2024). How Do Your Code LLMs Perform? Empowering Code Instruction Tuning with High-Quality Data. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.
Download Paper
Published in ICLR 2025, 2024
本文提出了一个全面的计算机科学基准测试集CS-Bench，用于评估大语言模型的计算机科学能力。
Recommended citation: Song, X., Diao, M., Dong, G., Wang, Z., Fu, Y., Qiao, R., Wang, Z., Fu, D., Wu, H., Liang, B., Zeng, W., Wang, Y., GongQue, Z., Yu, J., Tan, Q., & Xu, W. (2025). CS-Bench: A Comprehensive Benchmark for Large Language Models towards Computer Science Mastery. In International Conference on Learning Representations (ICLR 2025).
Download Paper
Published in NAACL 2024, 2024
本文研究了大语言模型在已知事实方面的幻觉现象。
Recommended citation: Jiang, C., Qi, B., Hong, X., Fu, D., Cheng, Y., Meng, F., Yu, M., Zhou, B., & Zhou, J. (2024). On Large Language Models' Hallucination with Regard to Known Facts. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics.
Download Paper
Published in COLING 2025, 2024
本文提出了PreAct方法，通过预测来增强智能体的规划能力。
Recommended citation: Fu, D., Huang, J., Lu, S., Dong, G., Wang, Y., He, K., & Xu, W. (2025). PreAct: Prediction Enhances Agent's Planning Ability. In Proceedings of the 2025 International Conference on Computational Linguistics (COLING 2025).
Download Paper
Published in Working in Progress, 2025
本文提出了DeepResearcher，一个基于强化学习的深度研究辅助系统。
Recommended citation: Zheng, Y.*, Fu, D.*, Hu, X.*, Cai, X., Ye, L., Lu, P., & Liu, P. (2024). DeepResearcher: Scaling Deep Research via Reinforcement Learning in Real-world Environments. arXiv preprint arXiv:2504.03160.
Download Paper