VICT Pulls Credit Assignment Out of the Verifier Instead of the Rollout, Changing Only the Training-Time Advantage Tensor

arXiv 2608.28128·medium signalXBlueskyLinkedInCopy link

VICT (arXiv 2608.28128, 2026-08-28, cs.AI/cs.LG) observes that RL for long-horizon LLM agents throws away structure it already has: the terminal verifier that judged success encodes the individual checks, but standard methods collapse it to a scalar and broadcast it across every action. VICT exposes executable or evidence-backed atoms from the verifier and traces them back to actions along dependency-valid proof edges, redistributing group-relative advantage only along those edges. It preserves the original terminal reward, abstains when evidence is incomplete, and requires no learned critic, process labels, branch rollouts or inference-time verifier access; on ALFWorld and WebShop it improves substantially over outcome-only training, with ablations ruling out dense atom rewards, final-commit credit, temporal proximity and sparsity as explanations.