Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.22083 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917358136721408 |
|---|---|
| author | Yang, Xi Lozano, Aurelie Abe, Naoki Bhavya Jha, Saurabh Zheutlin, Noah Arora, Rohan R. Deng, Yu Sow, Daby M. |
| author_facet | Yang, Xi Lozano, Aurelie Abe, Naoki Bhavya Jha, Saurabh Zheutlin, Noah Arora, Rohan R. Deng, Yu Sow, Daby M. |
| contents | Despite rapid progress in AI agents for enterprise automation and decision-making, their real-world deployment and further performance gains remain constrained by limited data quality and quantity, complex real-world reasoning demands, difficulties with self-play, and the lack of reliable feedback signals. To address these challenges, we propose a lightweight, model-agnostic framework for improving LLM-based enterprise agents via offline reinforcement learning (RL). The proposed Context Engineering via DT-MDP (DT-MDP-CE) framework comprises three key components: (1) A Digital-Twin Markov Decision Process (DT-MDP), which abstracts the agent's reasoning behavior as a finite MDP; (2) A robust contrastive inverse RL, which, armed with the DT-MDP, to efficiently estimate a well-founded reward function and induces policies from mixed-quality offline trajectories; and (3) RL-guided context engineering, which uses the policy obtained from the integrated process of (1) and (2), to improve the agent's decision-making behavior. As a case study, we apply the framework to a representative task in the enterprise-oriented domain of IT automation. Extensive experimental results demonstrate consistent and significant improvements over baseline agents across a wide range of evaluation settings, suggesting that the framework can generalize to other agents sharing similar characteristics in enterprise environments. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_22083 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP Yang, Xi Lozano, Aurelie Abe, Naoki Bhavya Jha, Saurabh Zheutlin, Noah Arora, Rohan R. Deng, Yu Sow, Daby M. Artificial Intelligence Despite rapid progress in AI agents for enterprise automation and decision-making, their real-world deployment and further performance gains remain constrained by limited data quality and quantity, complex real-world reasoning demands, difficulties with self-play, and the lack of reliable feedback signals. To address these challenges, we propose a lightweight, model-agnostic framework for improving LLM-based enterprise agents via offline reinforcement learning (RL). The proposed Context Engineering via DT-MDP (DT-MDP-CE) framework comprises three key components: (1) A Digital-Twin Markov Decision Process (DT-MDP), which abstracts the agent's reasoning behavior as a finite MDP; (2) A robust contrastive inverse RL, which, armed with the DT-MDP, to efficiently estimate a well-founded reward function and induces policies from mixed-quality offline trajectories; and (3) RL-guided context engineering, which uses the policy obtained from the integrated process of (1) and (2), to improve the agent's decision-making behavior. As a case study, we apply the framework to a representative task in the enterprise-oriented domain of IT automation. Extensive experimental results demonstrate consistent and significant improvements over baseline agents across a wide range of evaluation settings, suggesting that the framework can generalize to other agents sharing similar characteristics in enterprise environments. |
| title | A Context Engineering Framework for Improving Enterprise AI Agents based on Digital-Twin MDP |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2603.22083 |