Papers by Mei Wen
Towards Self-Evolving Agents: Enabling Autonomy through Interactive Experience Refinement (2026.findings-acl)
Copied to clipboard
Cheng Yang, Xuemeng Yang, Licheng Wen, Daocheng Fu, Jianbiao Mei, Rong Wu, Pinlong Cai, Yufan Shen, Nianchen Deng, Jia Xu, Botian Shi, Yu Qiao, Haifeng Li
| Challenge: | Large Language Models struggle with complex, multi-step operational tasks because they remain static during inference and cannot learn from past experience. |
| Approach: | They propose a framework that organizes cross-domain insights to facilitate orchestration of long-horizon workflows. |
| Outcome: | The proposed framework outperforms existing methods on the TAC productivity benchmark and shows strong cross-task transferability. |
SwiftPrune: Hessian-Free Weight Pruning for Large Language Models (2025.findings-emnlp)
Copied to clipboard
| Challenge: | a novel post-training pruning method relies on the Hessian matrix to perform pruning . current pruning methods are computationally intensive and lack performance due to second-order derivative calculations. |
| Approach: | They propose a Hessian-free weight pruning method that reduces computational burden . they use an Exponentially Weighted Moving Average technique to bypass weight sorting . |
| Outcome: | The proposed method achieves hardware-efficient model compression by eliminating computational intensive calculations. |
Illusions of the Gold Standard: A Large-scale Analysis of Human Evaluation Protocols for Long-form Text Generation (2026.acl-long)
Copied to clipboard
Katelyn X. Mei, Yi-Li Hsu, Minjoon Choi, Zongwan Cao, Chenjun Xu, Bingbing Wen, Su Lin Blodgett, Lucy Lu Wang
| Challenge: | a large-scale analysis of human evaluation protocols for long-form generation tasks is lacking in current practice . current protocols lack proper standardization and operationalization, which can limit validity of evaluation . |
| Approach: | They conduct a large-scale analysis of human evaluation protocols for long-form generation tasks in *CL conference papers from 2023–2025. |
| Outcome: | The proposed evaluation protocols lack standardization and operationalization, the authors show . they also find that the evaluation protocols are inadequate for specific domains and tasks . |
The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios (2026.findings-acl)
Copied to clipboard
Daocheng Fu, Jianbiao Mei, Rong Wu, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi
| Challenge: | Existing research mainly focuses on performance upper bounds in static environments, overlooking stochastic real-world deployment. |
| Approach: | They propose a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. |
| Outcome: | The proposed model evaluates agents in a dynamic evaluation environment that simulates a "trainee" agent continuously exploring a novel setting. |
Beyond Overlap Metrics: Rewarding Reasoning and Preferences for Faithful Multi-Role Dialogue Summarization (2026.findings-acl)
Copied to clipboard
| Challenge: | Existing methods for multi-role dialogue summarization favor surface-level imitation of references rather than genuine gains in faithfulness or alignment with human preferences. |
| Approach: | They propose a framework that couples explicit cognitive-style reasoning with reward-based optimization for multi-role dialogue summarization. |
| Outcome: | The proposed framework matches strong baselines on ROUGE and BERTScore, while in-depth analysis on SAMSum shows clear gains in factual faithfulness and model-based preference alignment. |