Answer First, Reason Later: Commitment Order in Diffusion LLMs

• URL: http://arxiv.org/abs/2608.05687v1
• Date: Thu, 06 Aug 2026 07:25:04 GMT
• Title: Answer First, Reason Later: Commitment Order in Diffusion LLMs
• Abstract summary: Masked diffusion language models (dLLMs) can commit tokens in any order.<n>We show that on reasoning tasks this freedom is instead the axis of failure.
• Score: 8.902793668615567
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Masked diffusion language models (dLLMs) can commit tokens in any order -- a freedom marketed as their core advantage over autoregressive decoding. We show that on reasoning tasks this freedom is instead the axis of failure. Logging every commitment during decoding of LLaDA-8B on GSM8K, we find that unconstrained (pure) decoding commits the final answer at 15-24% of the trajectory while half the reasoning region is still masked, and collapses to answer-only outputs on up to 90% of problems as the canvas grows. The cause is not the model's termination beliefs -- EOS "pressure" is nearly identical across decoders -- but reachability: whether the sampler may act on those beliefs at distant positions. A 2x2 prompt-decoder design shows that chain-of-thought helps only under ordered commitment (interaction +34.8 percentage points, 95% CI [26.8, 42.8]; without reasoning text the decoders are indistinguishable), an interaction we decompose into a collapse channel and an order channel and replicate on Dream-7B and MATH-500. A single-knob intervention -- frontier-gated commitment -- causally recovers the full gap (0.528 to 0.852) while preserving up to 4x parallel decoding, along a measured frontier whose optimal window flips from w=1 at full refinement to unconstrained at 8 tokens/step. Our results reframe existing window-style samplers, previously motivated by efficiency, as the minimal fix for a reasoning pathology they were never designed to address.

Related papers

• Constrained Decoding for Diffusion Language Models via Efficient Inference over Finite Automata [57.27430779838529]
  We present an exact and tractable algorithm for sampling from the constrained mean-field posterior under any constraint expressible as a finite automaton.<n>The approach guarantees constraint satisfaction by construction, supports both greedy and sampling-based decoding, and is compatible with parallel and block-wise decoding.<n> Empirical evaluations on Dream-7B and LLaDA-8 show substantial accuracy gains across various tasks.
  arXiv  Detail & Related papers  (2026-07-08T05:48:57Z)
• Doomed from the Start: Early Abort of LLM Agent Episodes via a Recall-Controlled Probe Cascade [14.63102636181275]
  Large language model (LLM) agents often waste inference compute by continuing multi-step trajectories that are already doomed to fail.<n>We study early failure prediction and inference-time early stopping for LLM agents using hidden-state probes.<n>We turn this signal into a recall-controlled abort cascade for reducing LLM agent inference costs.
  arXiv  Detail & Related papers  (2026-07-07T17:03:55Z)
• Roll Out and Roll Back: Diffusion LLMs are Their Own Efficiency Teachers [76.15132587294862]
  Wide-In, Narrow-Out (WINO) is a training-free decoding algorithm that enables revokable parallel generation.<n>WINO+ injects the verified denoising trajectories produced by WINO into model parameters, aligning training with efficient inference.<n>Experiments on LLaDA and MMaDA show that WINO improves both quality and efficiency, while WINO+ further strengthens this progression.
  arXiv  Detail & Related papers  (2026-05-16T11:27:40Z)
• LightThinker++: From Reasoning Compression to Memory Management [61.2260619973687]
  Large language models (LLMs) excel at complex reasoning, yet their efficiency is limited by the surging cognitive overhead of long thought traces.<n>We propose LightThinker, a method that enables LLMs to dynamically compress intermediate thoughts into compact semantic representations.<n>We evolve the framework into LightThinker++, introducing Explicit Adaptive Memory Management.
  arXiv  Detail & Related papers  (2026-04-04T10:46:09Z)
• Re-Mask and Redirect: Exploiting Denoising Irreversibility in Diffusion Language Models [0.0]
  Safety alignment in diffusion language models (dLLMs) relies on a single load-bearing assumption: committed tokens are permanent.<n>We show that by re-masking committed refusal tokens and injecting a short affirmative prefix, achieves 74-82% ASR on HarmBench.<n>We call this attack TrajHijack; it is the first trajectory-level attack on dLLMs, requires no computation, and generalizes across SFT and preference-optimized (VRPO) models.
  arXiv  Detail & Related papers  (2026-03-17T02:24:37Z)
• Latent Refinement Decoding: Enhancing Diffusion-Based Language Models by Refining Belief States [28.663951525871756]
  We introduce Latent Refinement Decoding (LRD), a two-stage framework with Latent Refinement and a Predictive Feedback Loop.<n>LRD improves accuracy while delivering speedups of up to 10.6x, making it a strong and versatile alternative for parallel sequence generation.
  arXiv  Detail & Related papers  (2025-10-13T06:38:13Z)
• Diffusion Language Models Know the Answer Before Decoding [56.96815863705218]
  Diffusion language models (DLMs) have emerged as an alternative to autoregressive approaches.<n>Our work highlights and leverage an overlooked property of DLMs early answer convergence.<n>We introduce Prophet, a training-free fast decoding paradigm that enables early commit decoding.
  arXiv  Detail & Related papers  (2025-08-27T15:40:25Z)
• What makes Reasoning Models Different? Follow the Reasoning Leader for Efficient Decoding [84.42056293290015]
  We analyze the token-level misalignment between reasoning and non-reasoning models.<n>Motivated by the Local Misalignment Diminish, we propose FoReaL-Decoding.<n>On four popular math-reasoning benchmarks, FoReaL-Decoding reduces theoretical FLOPs by 30 to 50% and trims CoT length by up to 40%.
  arXiv  Detail & Related papers  (2025-06-08T05:08:32Z)
• VeriThinker: Learning to Verify Makes Reasoning Model Efficient [52.74493506816969]
  Large Reasoning Models excel at complex tasks using Chain-of-Thought (CoT) reasoning.<n>Their tendency to overthinking leads to unnecessarily lengthy reasoning chains.<n>We introduce VeriThinker, a novel approach for CoT compression.
  arXiv  Detail & Related papers  (2025-05-23T14:17:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.