VETTA: Coordinating Turn- and Token-Level Credit Assignment for Multi-Turn LLM Agents

Excerpt

arXiv:2610.08402v1 Announce Type: new Abstract: Multi-turn LLM agents often receive sparse task feedback across several interactions, while generating each response token by token. This creates two related credit-assignment questions: which responses helped achieve the outcome, and which generation decisions mattered within each response? Existing methods typically focus on only one level: turn-level methods evaluate complete responses but do not distinguish the decisions within them; token-leve