Commit History
Add custom banner, upgrade conclusion style 4b7e335
Improve blog layout: badges, tables, visual hierarchy, quick start 1e570e7
Add YAML frontmatter to fix HF metadata warning 70d5da6
Rewrite blog: reposition as reliable tool-use benchmark e8700e9
Reframe: Adversarial Tool-Use Benchmark for Agentic RL e42edee
Yonghong commited on
Add Green Agent section to blog 40612ba
Yonghong commited on
Upload benchmark_results.png with huggingface_hub 6c42d60 verified
Upload training_curve.png with huggingface_hub 9d0f94c verified
Upload benchmark_results.png with huggingface_hub c16a776 verified
Update blog: 10 tasks avg 96.8, teammate improvements 168b01a
Yonghong commited on
Upload benchmark_results.png with huggingface_hub 3d4dcc3 verified
Add T9/T10 novel tasks to blog 173bbbe
Yonghong commited on
Add GRPO training curve to blog 3d6a5d7
Yonghong commited on
Upload training_curve.png with huggingface_hub 5f8e09c verified
Upload benchmark_results.png with huggingface_hub 0445e63 verified
Update blog with real Kimi results (94.4 avg) + fixed GRPO formula 739aac3
Yonghong commited on
Change author to MateFin 6b4058d
Yonghong commited on
Publish ComtradeBench blog — AgentBeats Phase 2 OpenEnv Challenge submission 06ff886
Yonghong commited on