Skip to content

Fix #511: Question about Code Availability for EMPO^2 Paper #520

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
JiwaniZakir wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix #511: Question about Code Availability for EMPO^2 Paper #520

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -46,6 +46,7 @@ To start using Agent-lightning, check out our [documentation](https://microsoft.

## ⚡ Articles

- *Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization* (EMPO²) arXiv paper. The corresponding implementation code is being prepared and will be released in this repository.
Copy link

Copilot AI Apr 16, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This new Articles entry breaks the established formatting in this section (other bullets include a date and a hyperlink to the referenced post/paper). Consider linking the paper title to its arXiv page and using the same date prefix (or an explicit "TBD" date) so the list stays consistent. Also consider including an ASCII alias like "EMPO^2" alongside "EMPO²" so users searching for the issue/paper name can find it reliably.

Suggested change
- *Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization* (EMPO²) arXiv paper. The corresponding implementation code is being prepared and will be released in this repository.
- TBD *Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization* (EMPO² / EMPO^2) arXiv paper. The corresponding implementation code is being prepared and will be released in this repository.

Copilot uses AI. Check for mistakes.
- 12/17/2025 [Adopting the Trajectory Level Aggregation for Faster Training](https://agent-lightning.github.io/posts/trajectory_level_aggregation/) Agent-lightning blog.
- 11/4/2025 [Tuning ANY AI agent with Tinker ✕ Agent-lightning](https://medium.com/@yugez/tuning-any-ai-agent-with-tinker-agent-lightning-part-1-1d8c9a397f0e) Medium. See also [Part 2](https://medium.com/@yugez/tuning-any-ai-agent-with-tinker-agent-lightning-part-2-332c5437f0dc).
- 10/22/2025 [No More Retokenization Drift: Returning Token IDs via the OpenAI Compatible API Matters in Agent RL](https://blog.vllm.ai/2025/10/22/agent-lightning.html) vLLM blog. See also [Zhihu writeup](https://zhuanlan.zhihu.com/p/1965067274642785725).
Expand Down
Loading