Published in arXiv 2026, 2026
Recommended citation: Zheng M, Zhou Y, Cao C, et al. SkillProx: Self-Evolving Agent Skills via Proximal Textual Gradient Descent. arXiv preprint arXiv:2608.07449, 2026.
Download Paper
Published in arXiv 2026, 2026
Recommended citation: Zhou Y, Cao C, Yang J, et al. LRAS: Advanced Legal Reasoning with Agentic Search. arXiv preprint arXiv:2601.07296, 2026.
Download Paper
Published in Preprints 2026, 2026
Recommended citation: Han S, Kou Z, Li R, et al. Trustworthy Legal Reasoning: A Comprehensive Survey. Preprints, 2026.
Download Paper
Published in arXiv 2025, 2025
Recommended citation: Cao C, Zhu Z, Zhu J, et al. Measuring Hong Kong Massive Multi-Task Language Understanding[J]. arXiv preprint arXiv:2505.02177, 2025.
Download Paper
Published in ICML 2026, 2026
Recommended citation: Cao C, Yang J, Li H, et al. Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification in Language Models. ICML, 2026.
Download Paper
Published in Technical Report, Shanghai AI Lab, 2026
Recommended citation: Cao C, Lin H, Zhong Z, et al. Unlocking Data Value in Finance: A Study on Distillation and Difficulty-Aware Training. arXiv preprint arXiv:2603.07223, 2026.
Download Paper
Published in EMNLP 2026, 2026
Recommended citation: Zhu Z, Cao C, Song Y et al. MedInsightBench: Evaluating Medical Analytics Agents Through Multi-Step Insight Discovery in Multimodal Medical Data. In Proceedings of EMNLP 2026.
Download Paper
Published in EMNLP 2026, 2026
Recommended citation: Zhou Y, Zheng M, Cao C, et al. LexAgentHallu: A Hierarchical Benchmark for Profiling Hallucinations in Legal Agents. In Proceedings of EMNLP 2026.
Published in ACL Findings 2026, 2026
Recommended citation: Luo J, Tian Y, Cao C, et al. From Storage to Experience: A Survey on the Evolution of LLM Agent Memory Mechanisms. Preprints, 2026.
Download Paper
Published in EMNLP 2025, 2025
Recommended citation: Cao C, Li M, Dai J, et al. Towards Advanced Mathematical Reasoning for LLMs via First-Order Logic Theorem Proving[J]. arXiv preprint arXiv:2506.17104, 2025.
Download Paper
Published in ACL Findings 2025, 2025
Recommended citation: Cao C, Zhu H, Ji J, et al. SafeLawBench: Towards Safe Alignment of Large Language Models[J]. arXiv preprint arXiv:2506.06636, 2025.
Download Paper
Published in Pacific-Asia Conference on Information Systems (PACIS) 2024, 2024
Recommended citation: Cao, Chuxue; Yuan, Ziqing; and Chen, Hailiang, "ScholarGPT: Fine-tuning Large Language Models for Discipline-Specific Academic Paper Writing" (2024). PACIS 2024 Proceedings. 1. https://aisel.aisnet.org/pacis2024/track04_dessci/track04_dessci/1
Download Paper
Published in IEEE International Conference on Bioinformatics and Biomedicine (BIBM) 2021, 2021
Recommended citation: C. Cao et al., "Medical Scene Graphs and Reasoning," 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), Houston, TX, USA, 2021, pp. 645-648, doi: 10.1109/BIBM52615.2021.9669882.
Download Paper