2 papers
cs.LG2025
SPARK: Stepwise Process-Aware Rewards for Reference-Free Reinforcement Learning
Salman Rahman, Sruthi Gorantla, Arpit Gupta +3
Process reward models (PRMs) that provide dense, step-level feedback have shown promise for reinforcement learning, yet their adoption remains limited by the need for expensive ste…
cs.LG2025
SABER: Small Actions, Big Errors -- Safeguarding Mutating Steps in LLM Agents
Alejandro Cuadron, Pengfei Yu, Yang Liu +1
Despite rapid progress in LLM agents, performance on long-horizon, tool-using tasks remains fragile. To better understand this fragility, we ask a simple question: \emph{do all act…