Sovereign 8s.is mirror of standardgalactic/PPP-Agent
Find a file
Repository files (latest commit first)
Filename Latest commit message Latest commit date
2025-11-06 16:56:40 -05:00
agents add code 2025-11-03 17:06:00 -05:00
envs update userville 2025-11-06 16:56:40 -05:00
LICENSE update userville 2025-11-06 16:04:48 -05:00
README.md update userville 2025-11-06 15:58:20 -05:00

Logo

PPP-Agent: Training Proactive and Personalized LLM Agents

License arXiv

PPP-Agent is an open-source framework for training LLM agents that are not only productive (task success) but also proactive (ask essential clarifying questions) and personalized (adapt to diverse user preferences). It includes UserVille, an interactive environment that turns existing agent benchmarks into multi-turn, preference-aware simulations.

Training Proactive and Personalized LLM Agents
Author: Weiwei Sun, Xuhui Zhou, Weihua Du, Xingyao Wang, Sean Welleck, Graham Neubig, Maarten Sap, Yiming Yang
https://arxiv.org/pdf/2511.02208


Highlights

  • UserVille: converts precise prompts into vague ones and simulates users with 20 configurable preferences.
  • PPP RL: multi-objective RL optimizing Productivity, Proactivity, Personalization jointly.
  • Plug-and-Play Tools: SWE (SWE-Bench & SWE-Gym) and Deep-Research (BrowseComp+) scaffolds.
  • User-Centric Metrics: effort-based proactivity + preference-following personalization.
  • Generalization: transfers to unseen preferences, simulators, and downstream tasks.

Stay Tuned


Cite

If you find this work useful, please consider citing our paper:

@article{sun2025pppagent,
  title={Training Proactive and Personalized LLM Agents},
  author={Sun, Weiwei and Zhou, Xuhui and Du, Weihua and Wang, Xingyao and Welleck, Sean and Neubig, Graham and Sap, Maarten and Yang, Yiming},
  journal={arXiv preprint arXiv:2511.02208},
  year={2025},
  url={https://arxiv.org/abs/2511.02208}
}

License

This project is licensed under the Apache License 2.0 - see the LICENSE file for details.