Wei Cai, Jian Zhao, Yuchen Yuan, Xuelong Li · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.28584 · cited by 0 works (OpenAlex) · open-access PDF
Авторегрессивные модели (ARMs) сталкиваются с «пузырем последовательности» в рассуждении, в то время как модели диффузионного языка (DLMs) предлагают параллелизм, но не имеют семантической согласованности. Чтобы решить оба ограничения, мы предлагаем Collaborative Reasoning Asymmetric Learning (CoRAL), гибридную структуру через архитектуру Asymmetric Planner-Executor (APE): DLM Planner генерирует K разнообразные траектории рассуждения параллельно, в то время как большой ARM Executor выбирает оптимальный план и синтезирует конечный ответ. Чтобы эффективно обучить Планера, мы вводим Reward-Guided Denoising for CoT (RDC), который интегрирует вознаграждения на основе
Machine translation (Meta M2M100); the English original follows.
Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) offer parallelism but lack semantic coherence. To addresses both limitations, we propose Collaborative Reasoning Asymmetric Learning (CoRAL), a hybrid framework via an Asymmetric Planner-Executor (APE) architecture: a DLM Planner generates K diverse reasoning trajectories in parallel, while a large ARM Executor selects the optimal plan and synthesizes the final answer. To train the Planner effectively, we introduce Reward-Guided Denoising for CoT (RDC), which integrates outcome-based rewards into the diffusion process to steer it toward goal-directed reasoning. Experiments on vision-language benchmarks show that CoRAL significantly outperforms prior diffusion-based methods and achieves competitive performance against strong ARMs, achieving both superior efficiency and quality.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Computer science, Artificial intelligence, Planner, Process (computing), Face (sociological concept), Plan (archaeology)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28584, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange