STT-Arena introduces a benchmark for adaptive replanning under spatio-temporal disruptions in tool-using agents, with SOTA models below 40% accuracy and a new STT-Agent-4B outperforming them.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
STT-Arena introduces a benchmark for adaptive replanning under spatio-temporal disruptions in tool-using agents, with SOTA models below 40% accuracy and a new STT-Agent-4B outperforming them.