{"ID":3083681,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T07:39:45.869976485Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.06245","arxiv_id":"2606.06245","title":"MPCoT: Reward-Guided Multi-Path Latent Reasoning for Test-Time Scalable Vision-Language-Action","abstract":"Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited inference-time deliberation. Explicit chain-of-thought can increase reasoning depth, but introduces token latency and an indirect text-to-action interface. We propose MPCoT, a reward-guided multi-path latent reasoning framework that initializes $M$ hypotheses, refines them for K weight-tied steps, and softly aggregates them before action decoding. A training-only path-preference objective evaluates candidate action branches with expert-action consistency, world-model/VLM-based progress, and success feedback to align the latent path scorer with downstream execution quality. MPCoT preserves the original 8-step action interface, generates zero reasoning tokens, and exposes configurable inference controls (K,M). Under matched protocols on LIBERO and CALVIN, MPCoT improves long-horizon performance, with ablations confirming depth-width effects, confidence-weighted aggregation, and reward-guided path supervision.","short_abstract":"Vision-Language-Action (VLA) policies remain brittle in long-horizon and high-uncertainty control, where one-pass action decoding provides limited inference-time deliberation. Explicit chain-of-thought can increase reasoning depth, but introduces token latency and an indirect text-to-action interface. We propose MPCoT,...","url_abs":"https://arxiv.org/abs/2606.06245","url_pdf":"https://arxiv.org/pdf/2606.06245v1","authors":"[\"Boyang Zhang\",\"Lianlei Shan\"]","published":"2026-06-04T14:48:44Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\"]","methods":"[]","has_code":false}