Matched-Context Group Policy Optimization for LLM Agent Training
arXiv:2610.13755v1 Announce Type: cross Abstract: Training long-horizon language model agents requires assigning credit to intermediate decisions from sparse terminal feedback. Within a finite group of sibling rollouts, useful action comparisons depend on their context, evidence for both alternatives, and how that evidence enters learning. We propose Matched-Context Group Policy Optimization (MCGPO), a procedure for constructing weighted action preferences from already collected trajectories. M…