{"ID":5554325,"CreatedAt":"2026-07-02T02:11:27.934456424Z","UpdatedAt":"2026-07-04T16:50:11.910852832Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.01170","arxiv_id":"2607.01170","title":"Diffusion-GR2: Diffusion Generative Reasoning Re-ranker","abstract":"Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces. To reduce this cost, block-diffusion language models decode many positions in parallel over a few denoising steps and are substantially faster, yet naively converting an AR re-ranker into one opens two accuracy gaps: (1) a structural gap: answer positions are denoised in parallel and scored independently, so the decoder emits invalid rankings (duplicated, dropped, or out-of-set identifiers) that AR avoids through left-to-right masking; and (2) a distributional gap: fine-tuning the converted model on fixed teacher trajectories is off-policy relative to its own decoding at inference, leaving a residual accuracy gap. To close both gaps while keeping the speedup, we propose \\textbf{Diffusion-GR2}, a recipe that converts our AR reasoning re-ranker (GR2) into a block-diffusion re-ranker. First, conversion fine-tuning (CFT) adapts the AR-initialized diffusion model to denoise the answer into a valid permutation on its own, without an external constrained decoder. Next, on-policy distillation (OPD) then supervises the model on its own decoded trajectories with dense per-token targets from the AR teacher. Finally, we apply a reinforcement-learning (RL) stage against a re-ranking reward on top of OPD's on-policy policy. Experiments on Amazon Beauty demonstrate that Diffusion-GR2 recovers to near-parity with the AR re-ranker, while block-parallel decoding raises decode throughput by $2.4$--$3.5\\times$ at the model's reasoning output length. Ablations show that CFT recovers most of the conversion gap, and that on-policy distillation further closes it to the AR reference.","short_abstract":"Generative reasoning re-rankers achieve strong recommendation accuracy by emitting a chain-of-thought before re-ordering a candidate list, but they are slow at inference: an autoregressive (AR) decoder spends one sequential forward pass per reasoning token, and the reasoning trace far exceeds the ranking it produces. T...","url_abs":"https://arxiv.org/abs/2607.01170","url_pdf":"https://arxiv.org/pdf/2607.01170v1","authors":"[\"Zhuoxuan Zhang\",\"Kangqi Ni\",\"Yuhang Chen\",\"Mingfu Liang\",\"Xiaohan Wei\",\"Yunchen Pu\",\"Fei Tian\",\"Chonglin Sun\",\"Frank Shyu\",\"Adam\",\"Song\",\"Sandeep Pandey\",\"Luke Simon\",\"Tianlong Chen\",\"Xi Liu\"]","published":"2026-07-01T17:02:20Z","proceeding":"cs.IR","tasks":"[\"cs.IR\",\"cs.AI\"]","methods":"[\"Diffusion Model\",\"Language Model\"]","has_code":false}