Duplicated from open-agent-leaderboard/react-shortlisting

Exgentic
/

react-shortlisting

agent-evaluation

Model card Files Files and versions

React + Shortlisting

This is a tracking repo for React + Shortlisting, used by the Open Agent Leaderboard to report evaluation results on HuggingFace.

ReAct agent with tool shortlisting — dynamically filters available tools per step to reduce context and improve accuracy.

Framework: litellm + exgentic
Leaderboard: Open Agent Leaderboard
Paper: arXiv:2602.22953

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Paper for Exgentic/react-shortlisting

General Agent Evaluation

Paper • 2602.22953 • Published Feb 26 • 12

Evaluation results

Overall
on open-agent-leaderboard/results View evaluation results source leaderboard

model: Claude Opus 4.5
0.62 ^*
on open-agent-leaderboard/results View evaluation results source leaderboard

model: DeepSeek V3.2
0.45 ^*
Appworld on open-agent-leaderboard/results View evaluation results source leaderboard

0.64 ^*
Browsecomp Plus on open-agent-leaderboard/results View evaluation results source leaderboard

0.49 ^*
Swebench on open-agent-leaderboard/results View evaluation results source leaderboard

0.61 ^*
Taubench Airline on open-agent-leaderboard/results View evaluation results source leaderboard

0.66 ^*
Taubench Retail on open-agent-leaderboard/results View evaluation results source leaderboard

0.78 ^*
Taubench Telecom on open-agent-leaderboard/results View evaluation results source leaderboard

0.76 ^*