Accepted Papers

1. Designer-RSI: Evolving Procedural Memory in the Wild for Agentic Graphic Design [Oral]

   Hongyang Du, Lan Yan, Christian Flores, Asim Kadav

2. CONTRAMEM: Learning Self-Evolving Procedural Memory from Contrasting Multi-Model Trajectories [Oral]

   Zheyuan Deng, binghang lu, Hanqi Feng, Shirley Huang, Dianzhuo Wang, Yuanda Xu, Zhiwei Zhang, Yige Sun, Changhong Mou, Runyu Zhang, Yuexing Hao, Barnabas Poczos, Xiaomin Li

3. Passing the Accuracy SLA While Failing the Fairness One: Disparity Drift and Its Cost in Continually Updated Classifiers [Oral]

   Miles Bliey, Keira Chatwin

4. DKL: Decoupled Knowledge Learning for Instruction-Tuned Language Models [Oral]

   Kushagra Bhushan, Meghanadh Pulivarthi, Sai Krishna Reddy Sathi, Gaurav Pandey, Sonam Gupta, Vineet Kumar, Jaydeep Sen, Yatin Nandwani, Dinesh Raghu, Sachindra Joshi

5. Conservative-First Release Mitigates Verifier Overfitting in Generated Agent Workflows [Oral]

   Shijin Wang, Yuanyuan Tan, Wenqi Zheng, Jinming He, Tongzhou Jiang

6. Towards continual in-context learning via training Cartridges at test time [Oral]

   Hongyi Huang, Kaitlyn Wang, Ajay Anubolu, Shayan Talaei, Arshia Soltani Moakhar, Azalia Mirhoseini, Amin Saberi

7. When Should a Working Agent Change? Reversible Workflow Replacement for Continual Agent-System Adaptation [Poster]

   Ali Atiah Alzahrani

8. Position: The MLOps-to-LLMOps Transition Demands a New Operational Paradigm [Poster]

   Rudrendu Kumar Paul, Sourav Nandy

9. Memory as the Organization of Knowledge: Four Neural Principles for Adaptive Agents [Poster]

   Xin Li

10. HyperSkill: Self-Evolving LLM Agents via Hypergraph-Structured Skill Memory [Poster]

    Ruiyao Xu, Tiankai Yang, Wei-Chieh Huang

11. Measurable by Construction: Contradiction Density and the Evaluation of Belief-Forming Memory [Poster]

    Manas Vardhan, Yug Aditi gupta

12. Assurance Has a Half-Life: Why Continual Learning Breaks Point-in-Time Governance for Enterprise AI Agents [Poster]

    Shivaraman Parthasarathy

13. AURA: Amortized, User-Conditioned Reranking Adapters for Personalized LLM Agents [Poster]

    Alex Wang, Balaji Boopal, Rachel Pothen, Ninad Vivek Rao, Yi Zhang, Vishal Amarlal Khatri, Amit Dhanda, Sina Amini Niaki, Brian Verkhovsky

14. EconSkills: Studying Skill Transfer and Retrieval for Web Agents on Live Economic Data [Poster]

    Yinzhu Quan, Zefang Liu

15. Change Passports: A Machine-Readable Standard for Auditable Artifact Promotion in Continually-Learning Agents [Poster]

    Enrique Zueco, David Scott Lewis, Haley Yi, Karl Wang, Junhan Wang

16. UniSD: Towards A Unified Self-Distillation Framework for Large Language Models [Poster]

    Yiqiao Jin, Yiyang Wang, Lucheng Fu, Yijia Xiao, Yinyi Luo, Haoxin Liu, B. Aditya Prakash, Chao Zhang, Josiah Hester, Jindong Wang, Srijan Kumar

17. VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering [Poster]

    Kang Li, Lu He, Sandarsita Guntupalli

18. Deliberation Memory: Preserving How Humans and Heterogeneous Agents Reach, Contest, and Revise Decisions [Poster]

    Gustavo Castañeda Heras

19. Privileged Context as Drift in On-Policy Self-Distillation [Poster]

    Nick Rui, Ravenor Davion

20. ASTRA - Agentic System for Ticket Resolution and Analysis [Poster]

    Shashidhar Reddy Javaji, Mohamed Trabelsi, Jin Cao, Huseyin Uzunalioglu

21. EchoPath: Execution-Level Replayable Memory for GUI Agents [Poster]

    Yao Zhao, Aditya Shanmugham, Swastik Roy, Yanxun Xu

22. RECAST: dynamic REplay for Counterfactual Agentic Simulation from static Trajectories [Poster]

    Ye Li, Jian Tan, Fan Bu, Derek Engi, Yuqing Gao

23. REM: What to Store, When to Recall, What to Forget in Experience Memory for Coding Agents [Poster]

    Xinyi Lisa Chen, Pedro Herrero-Vidal, Xiaohan Chen, Xiaojing Yu, Cris Liu, Bingqing Song, Bin Xu, You-Lin Chen

24. Continual Evaluation for Enterprise Agent Governance: Architecture and Evidence from a Policy Layer [Poster]

    Shaishav Pindadi

25. Continuous Process-Level Evaluation for Evolving Enterprise AI Agent Skills [Poster]

    Ngoc Phuoc An Vo, Aarya Doshi, Vadim Sheinin

26. Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails [Poster]

    Zhou Yu, Bin Bi, Shiva Kumar Pentyala, Shubham Mehrotra, SOUGATA CHAUDHURI, Shilpa Bhagavath, Zeyuan Chen, Ran Xu, James Zhu, Sitaram Asur, Phil L Mui

27. PRISM: Prompt-Refined In-Context System Modeling for Financial Retrieval [Poster]

    Chun Chet Ng, Jia Yu Lim, Zhen Hao Chu, Yixi Zhou, Low Wei Zeng

28. Continual Learning for Enterprise Agents is a Change-Control Problem [Poster]

    Kenneth D. Aiello, Jennifer Mallette, Anna Podgornyak, Vincent Shiau, Narayanan Alavandar, Tony Vachino

29. Training-Free Continual Learning for Multimodal Forecasting via Prompt Evolution [Poster]

    Laurent Mombaerts, Jonathan Taws, Dinesh Yadav Gaddam, Jacopo Pio Gargano, Srijan Tiwari, Shreyas Rajesh

30. Adaptive Auto-Harness: Sustained Self-Improvement on Open-Ended Task Streams [Poster]

    Zewen Liu, Zhan Shi, Yisi Sang, Bing He, Minhua Lin, Tianxin Wei, Dakuo Wang, Benoit Dumoulin, Wei Jin, Hanqing Lu

31. ESCROW: Guarded and Dual-Objective Continual Maintenance for Agents in Policy-Governed Enterprise Workflows [Poster]

    Ruoqi Shu, Chen Dan, Xuhui Wang, Tianhua Xu, Mengxi luo, Yanming Mai, Bo Wan

32. Benchmarking Continual Learning in Orchestration Agents [Poster]

    Shreyas Rajesh, Srijan Tiwari, Jonathan Taws, Laurent Mombaerts, Jacopo Pio Gargano

33. Sensitive but Not Specific: Log-Side Screening for Reward Hacking in Continually Updated Agents [Poster]

    Jules Roussel

34. Continual Enterprise World Model Discovery in Dynamic Systems [Poster]

    Shambhavi Mishra, David Vazquez, Perouz Taslakian, Marco Pedersoli, Jose Dolz, Issam H. Laradji

35. When the Cross-Silo Federation Goes Offline: Continual Learning for Site Onboarding with Limited Unlabeled Data [Poster]

    Ahmadreza Eslaminia, Klara Nahrstedt, Chenhui Shao

36. Beyond Leaderboards: Continual, Task-Specific LLM Evaluation for Enterprise Finance [Poster]

    Anup K. Kalia, Daxin Niu, Dong Wang, Prem Melville

37. A Self-Improving Agent that Grows its Own DSL: Oracle-Free Operator Induction for Exact Question Answering [Poster]

    Yun-Shiuan Chuang, Yirou Ge, Yixi Li, Yiming Bian, Uma Kona, Linsey Pang, Prakhar Mehrotra

38. Agentic Context Learning with Self-Discovered Specification [Poster]

    Jike Zhong, Ming Li, Yuxiang Lai, Ziyan Yang, Jingyu Xie, Zheda Mai

39. When Accumulated Memory Starts to Hurt: Forgetting and Cost in Non-Parametric Continual Adaptation [Poster]

    SAIKUMAR DANDLA, Harish Y V S

40. Scaling Proactive Compute: When the Agent Anticipates the Task [Poster]

    Shayan Talaei, Jirat Chiaranaipanich, Amirreza Zeinali, Azalia Mirhoseini, Amin Saberi