TMAS is a new multi-agent synergy framework with experience and guideline banks plus hybrid-reward RL that delivers stronger iterative test-time scaling than prior structured methods on reasoning benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
method 1
citation-polarity summary
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1roles
method 1polarities
use method 1representative citing papers
citing papers explorer
-
TMAS: Scaling Test-Time Compute via Multi-Agent Synergy
TMAS is a new multi-agent synergy framework with experience and guideline banks plus hybrid-reward RL that delivers stronger iterative test-time scaling than prior structured methods on reasoning benchmarks.