arXiv Computation and Language October 28, 2026 By Mingyu Zhao, Shuhang Lin, Ligong Han, Xiaojing Yu, Zhenting Wang, Yifei Pang, Yang Zhou, Dimitris N. Metaxas

Metacognitive Decoding: Efficient Inference for Diffusion Language Agents

Read the original on arXiv Computation and Language →

The paper introduces a metacognitive controller that optimizes diffusion language models for agent tasks by deciding when to finalize tokens and how far to generate, thereby reducing computation. The lightweight plug‑in is trained on agent trajectories to balance correctness and generation cost. Experiments on five benchmarks show an average 20.6% reduction in inference FLOPs while keeping task accuracy competitive.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computation and Language.

arXiv Machine Learning

Sep 30

FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

arXiv:2609.36202v1 Announce Type: cross Abstract: Gradient-based reward guidance provides a flexible way to use downstream reward models to control masked diffusion language models at inference time....

By Darshan Thaker, Lachlan Ewen MacDonald, Ren\'e Vidal

llms diffusion reinforcement-learning benchmarks

arXiv Machine Learning

Aug 4

Just on Time: Token-Level Early Stopping for Diffusion Language Models

arXiv:2602. 11133v2 Announce Type: replace Abstract: Diffusion language models generate text through iterative refinement, a process that is often computationally inefficient because many tokens reach stability long before the final denoising step.

By Zakhar Kohut, Severyn Shykula, Mykola Vysotskyi, Serhii Dmytryshyn, Dmytro Khamula, Michal Zakrzewski, Damian Rynczak, Jacek Ma{\l}ecki, Taras Rumezhak, Volodymyr Karpiv

llms diffusion nlp fine-tuning benchmarks

arXiv AI

Jun 9

WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

arXiv:2606. 07710v1 Announce Type: cross Abstract: The autoregressive nature of large language models (LLMs) remains a significant bottleneck for inference, particularly in complex agentic workloads.

By Young D. Kwon, Miles Williams, Rui Li, Alexandros Kouris, Stylianos I. Venieris

llms agents diffusion efficiency benchmarks

arXiv AI

Jun 16

Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens

arXiv:2606. 16847v1 Announce Type: cross Abstract: Diffusion Large Language Models (dLLMs) offer a promising avenue for parallel generation but face a trade-off between decoding speed and quality.

By Yizhen Yao, Qinglin Zhu, Runcong Zhao, Xiangxiang Dai, Yanzheng Xiang, Yulan He, Lin Gui

llms rag diffusion efficiency benchmarks

Hugging Face Trending Papers

Jul 21

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

Speculative decoding, in which a lightweight draft model first generates a draft sequence that is then verified in parallel by the target model, has become a prevalent paradigm for accelerating large language model inference. Recent work such as DFlash further boosts drafting efficiency by leveraging diffusion drafters, whose parallel denoising mechanism enables draft generation in a single forward pass.

llms diffusion efficiency benchmarks

arXiv AI

Jul 17

Mask-Aware Policy Gradients for Diffusion Language Models

arXiv:2607. 15200v1 Announce Type: cross Abstract: Reinforcement learning has proven effective for improving reasoning in large language models, but extending it to Masked Diffusion Language Models (MDLMs) remains challenging due to the intractability of the log-likelihood estimation.

By Haran Raajesh, Kulin Shah, Adam Klivans, Philipp Kr\"ahenb\"uhl

llms diffusion reinforcement-learning benchmarks

One email a morning, machine-written

Related stories

FastGuide: Accelerating Reward Guidance for Diffusion Large Language Models

Just on Time: Token-Level Early Stopping for Diffusion Language Models

WhiFlash: Accelerating Speculative Decoding with Token-Level Cross-Paradigm Routing

Follow the Latent Roadmap: Navigating Revocable Decoding for Diffusion LLMs with Anchor Tokens

AdaFlash: Adaptive Speculative Decoding via On-Policy Distilled Diffusion Drafters

Mask-Aware Policy Gradients for Diffusion Language Models