Teach the Magnitude, Not the Direction: Verifier-Anchored Credit Assignment for Multi-Turn Multi-Step LLM Agents.

arXiv:2608.13179v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) directly optimizes verifier-defined outcomes for multi-turn tool-use agents, yet its trajectory-level credit assignment conflates heterogeneous per-turn o