ForestBench
Explore score history ↗ForestBench evaluates multi-agent collaboration by representing MAS traces as unified collaboration graphs, comparing them against query-specific reference forests of successful graphs, and scoring structural similarity with a metric panel.
- Released
- 2026-08-09
- Institutions
- Southwest University · Tencent (China) · Chinese Academy of Sciences
- Evaluates
- Agents, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
ForestBench paper
No reported scores are on record for this benchmark yet.