1 Release published by 1 person

• v0.4.0

  published Feb 11, 2025

7 Pull requests merged by 3 people

• fixing openai api typo for logprobs

  #224 merged Feb 26, 2025

• adding log_prob option for chat models

  #219 merged Feb 25, 2025

• Add missing agent imports

  #223 merged Feb 25, 2025

• Add VLLMChatModel support to chat API

  #220 merged Feb 20, 2025

• Update repro o1 o3 mini

  #216 merged Feb 12, 2025

• moved this post_hoc_get_action to private codebase

  #218 merged Feb 11, 2025

• Add new agent configurations for Claude Sonnet 3.5 and vision models

  #213 merged Feb 6, 2025

4 Pull requests opened by 4 people

• [WIP] Multitool envs

  #214 opened Feb 7, 2025

• Add Tools for Managing Agent Traces in Hugging Face Datasets

  #217 opened Feb 10, 2025

• Add-claude-3.7 to repro journal

  #222 opened Feb 25, 2025

• adding resample benchmark objects

  #226 opened Feb 26, 2025

3 Issues closed by 2 people

• Adding instructions for using the `parallel_backend="ray"` default option

  #139 closed Feb 10, 2025

• Low Cost estimate in agent-xray

  #203 closed Feb 7, 2025

• Solve dependencies for python 3.13

  #212 closed Feb 4, 2025

3 Issues opened by 3 people

• How to evaluate an optional subset of the benchmark?

  #225 opened Feb 26, 2025

• disable dependencies to increase parallelism

  #221 opened Feb 20, 2025

• dockerizing AgentLab

  #211 opened Feb 3, 2025

8 Unresolved conversations

Sometimes conversations happen on old items that aren’t yet closed. Here is a list of all the Issues and Pull Requests with unresolved conversations.

• Error Analysis API

  #208 commented on Feb 20, 2025 • 2 new comments

• Torch/Architecture clashes for Mac users

  #209 commented on Feb 4, 2025 • 0 new comments

• Wrong reported trajectories with parallel seeds in xray

  #207 commented on Feb 7, 2025 • 0 new comments

• Providing trajectories in the leaderboard

  #193 commented on Feb 7, 2025 • 0 new comments

• Prepare all SequentialStudies

  #162 commented on Feb 7, 2025 • 0 new comments

• logs in ray

  #134 commented on Feb 7, 2025 • 0 new comments

• Removing global to make it gradio usable across multiple sessions

  #186 commented on Feb 7, 2025 • 0 new comments

• Generalized AgentLab Env

  #210 commented on Jan 28, 2025 • 0 new comments