ICML 2025 Workshop on Programmatic Representations for Agent Learning

Accepted papers (26)

Fetched from OpenReview (v2) on 2026-06-10.

1. ☆Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

   Mingzhe Du, Anh Tuan Luu, Yue Liu, Yuhao QING, Dong HUANG, Xinyi He, Qian Liu, Zejun MA, See-Kiong Ng · PDF

2. ☆Discovering Logic-Informed Intrinsic Rewards to Explain Human Policies

   Chengzhi Cao, Yinghao Fu, Chao Yang, Shuang Li · PDF

3. ☆DyPO: Dynamic Policy Optimization for Multi-Turn Interactive Reasoning

   Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Ng · PDF

4. ☆EditLord: Learning Code Transformation Rules for Code Editing

   Weichen Li, Albert Jan, Baishakhi Ray, Junfeng Yang, Chengzhi Mao, Kexin Pei · PDF

5. ☆FormulaCode: Evaluating Agentic Superoptimization on Large Codebases

   Atharva Sehgal, James Hou, Swarat Chaudhuri, Jennifer J. Sun, Yisong Yue · PDF

6. ☆How Robust Reinforcement Learning Enables Courier-Friendly Route Planning for Last-Mile Delivery?

   Ziying Jia, Zeyu Dong, Miao Yin, Sihong He · PDF

7. ☆Improving LLM Agent Planning with In-Context Learning via Atomic Fact Augmentation and Lookahead Search

   Samuel Holt, Max Ruiz Luyten, Thomas Pouplin, Mihaela van der Schaar · PDF

8. ☆Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces

   Anjiang Wei, Allen Nie, Thiago S. F. X. Teixeira, Rohan Yadav, Wonchan Lee, Ke Wang, Alex Aiken · PDF

9. ☆Inefficiencies of Meta Agents for Agent Design

   Batu El, Mert Yuksekgonul, James Zou · PDF

10. ☆InstructFlow: Adaptive Symbolic Constraint-Guided Code Generation for Long-Horizon Planning

    Haotian Chi, Zeyu Feng, Yueming Lyu, Chengqi Zheng, Linbo Luo, Yew-Soon Ong, Ivor Tsang, Hechang Chen, Yi Chang, Haiyan Yin · PDF

11. ☆Interpretable Reward Modeling with Active Concept Bottlenecks

    Sonia Laguna, Kasia Kobalczyk, Julia E Vogt, Mihaela van der Schaar · PDF

12. ☆Large Language Models Can Think and Act Probabilistically

    Kou Misaki, Takuya Akiba · PDF

13. ☆Learned Representations Enhance Multi Agent Path Planning

    Marius Captari, Herke van Hoof · PDF

14. ☆Learning Game-Playing Agents with Generative Code Optimization

    Zhiyi Kuang, Ryan Rong, YuCheng Yuan, Allen Nie · PDF

15. ☆Learning to Discover Abstractions for LLM Reasoning

    Yuxiao Qu, Anikait Singh, Yoonho Lee, Amrith Setlur, Ruslan Salakhutdinov, Chelsea Finn, Aviral Kumar · PDF

16. ☆Leveraging LLM-based sentiment analysis for portfolio optimization with proximal policy optimization

    Kemal Kirtac, Guido Germano · PDF

17. ☆Lifelong Experience Abstraction and Planning

    Peiqi Liu, Leslie Pack Kaelbling, Joshua B. Tenenbaum, Jiayuan Mao · PDF

18. ☆Making LLMs Program Interpreters via Execution Trace Chain of Thought

    Koshi Eguchi, Takuya Akiba · PDF

19. ☆Optimizing Agentic Architectures for Cybersecurity Tasks with Trace

    Anish Chaudhuri, Prerit Choudhary, Max Piasevoli, Shannon Xiao, Allen Nie · PDF

20. ☆ReasonRec: A Reasoning-Augmented Multimodal Agent for Unified Recommendation

    Yihua Zhang, Xi Liu, Xihuan Zeng, Mingfu Liang, Jiyan Yang, Rong Jin, Wen-Yen Chen, Yiping Han, Hao Ma, Bo Long, Huayu Li, Buyun Zhang, Liang Luo, Sijia Liu, Tianlong Chen · PDF

21. ☆Representing Prompting Patterns with PDL: Compliance Agent Case Study

    Mandana Vaziri, Louis Mandel, Yuji Watanabe, Hirokuni Kitahara, Martin Hirzel, Anca Sailer · PDF

22. ☆Searching Latent Program Spaces

    Matthew Macfarlane, Clément Bonnet · PDF

23. ☆Sketch-Plan-Generalize : Learning and Planning with Neuro-Symbolic Programmatic Representations for Inductive Spatial Concepts

    Namasivayam Kalithasan, Sachit Sachdeva, Gurarmaan Singh Panjeta, Harsh Himanshu Vora, Himanshu Gaurav Singh, Vishal Bindal, Arnav Tuli, Divyanshu Agarwal, Rohan Paul, Parag Singla · PDF

24. ☆Time to Impeach LLM-as-a-Judge: Programs are the Future of Evaluation

    Tzu-Heng Huang, Harit Vishwakarma, Frederic Sala · PDF

25. ☆Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

    Fan Nie, Lan Feng, Haotian Ye, Weixin Liang, Pan Lu, Huaxiu Yao, Alexandre Alahi, James Zou · PDF

26. ☆Zero-Shot Instruction Following in RL via Structured LTL Representations

    Mattia Giuri, Mathias Jackermeier, Alessandro Abate · PDF