Showing cs.AIShow all
2 papers · 1 filter
cs.AI2026
ASCT: Attentive Search over Counterfactual Trees for Credit Assignment in Agentic Reinforcement Learning
Yang Li, Jinhan Yang, hai liu +8
Terminal utility evaluates a complete agentic workflow, but learning requires credit for the decisions within it. We introduce Attentive Search over Counterfactual Trees (ASCT), a…
cs.AI2026
Agent-UCT: Upper Confidence Bounds Applied to Trees for Cost-Aware Agentic Workflow Optimization
Yang Li, Hai Liu, Dian Shao +9
Workflow search pays for complete quality observations, whose execution cost changes as reusable prefixes accumulate. AgentUCT uses an economic model of the remaining evaluation co…