AgenticSTS Benchmark
Explore score history ↗AgenticSTS is a reproducible long-horizon agent testbed that evaluates bounded, typed-retrieval memory configurations through game outcomes and controlled ablations.
- Released
- 2026-07-02
- Institutions
- Shanghai Jiao Tong University · Avaya (Bermuda) · Shanghai Innovation Institute
- Evaluates
- Agents, General AI, Language & Knowledge
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- ai-reviewed
AgenticSTS paper
No reported scores are on record for this benchmark yet.