DLLM Agent: See Farther, Run Faster

• URL: http://arxiv.org/abs/2602.07451v2
• Date: Tue, 10 Feb 2026 02:35:16 GMT
• Title: DLLM Agent: See Farther, Run Faster
• Authors: Huiling Zhen, Weizhe Lin, Renxi Liu, Kai Han, Yiming Li, Yuchuan Tian, Hanting Chen, Xiaoguang Li, Xiaosong Li, Chen Chen, Xianzhi Yu, Mingxuan Yuan, Youliang Yan, Peifeng Qin, Jun Wang, Yu Wang, Dacheng Tao, Yunhe Wang,
• Abstract summary: Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties.<n>We study this in a controlled setting by instantiatingDLLM and AR backbones within the same agent workflow.<n>We find thatDLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup.
• Score: 94.74432470237817
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Diffusion large language models (DLLMs) have emerged as an alternative to autoregressive (AR) decoding with appealing efficiency and modeling properties, yet their implications for agentic multi-step decision making remain underexplored. We ask a concrete question: when the generation paradigm is changed but the agent framework and supervision are held fixed, do diffusion backbones induce systematically different planning and tool-use behaviors, and do these differences translate into end-to-end efficiency gains? We study this in a controlled setting by instantiating DLLM and AR backbones within the same agent workflow (DeepDiver) and performing matched agent-oriented fine-tuning on the same trajectory data, yielding diffusion-backed DLLM Agents and directly comparable AR agents. Across benchmarks and case studies, we find that, at comparable accuracy, DLLM Agents are on average over 30% faster end to end than AR agents, with some cases exceeding 8x speedup. Conditioned on correct task completion, DLLM Agents also require fewer interaction rounds and tool invocations, consistent with higher planner hit rates that converge earlier to a correct action path with less backtracking. We further identify two practical considerations for deploying diffusion backbones in tool-using agents. First, naive DLLM policies are more prone to structured tool-call failures, necessitating stronger tool-call-specific training to emit valid schemas and arguments. Second, for multi-turn inputs interleaving context and action spans, diffusion-style span corruption requires aligned attention masking to avoid spurious context-action information flow; without such alignment, performance degrades. Finally, we analyze attention dynamics across workflow stages and observe paradigm-specific coordination patterns, suggesting stronger global planning signals in diffusion-backed agents.

Related papers

• DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents [31.08047797205678]
  Diffusion Large Language Models (dLLLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm.<n>Despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation termed as 1) Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm.<n>In this paper, we propose an optimization framework for dLLM-based Search Agents.
  arXiv  Detail & Related papers  (2026-02-03T09:12:08Z)
• The Bitter Lesson of Diffusion Language Models for Agentic Workflows: A Comprehensive Reality Check [54.08619694620588]
  We present a comprehensive evaluation of dLLMs across two distinct agentic paradigms: Embodied Agents and Tool-Calling Agents.<n>Our results on Agentboard and BFCL reveal a "bitter lesson": current dLLMs fail to serve as reliable agentic backbones.
  arXiv  Detail & Related papers  (2026-01-19T11:45:39Z)
• AgentPRM: Process Reward Models for LLM Agents via Step-Wise Promise and Progress [71.02263260394261]
  Large language models (LLMs) still encounter challenges in multi-turn decision-making tasks.<n>We build process reward models (PRMs) to evaluate each decision and guide the agent's decision-making process.<n>AgentPRM captures both the interdependence between sequential decisions and their contribution to the final goal.
  arXiv  Detail & Related papers  (2025-11-11T14:57:54Z)
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering [51.07491603393163]
  tAgent is a framework that formulates multi-agent QA as a knowledge-graph-guided routing problem supervised by empirical performance signals.<n>By leveraging soft supervision and weighted aggregation of agent outputs, Agent learns principled collaboration schemes that capture the complementary strengths of diverse agents.
  arXiv  Detail & Related papers  (2025-10-06T23:20:49Z)
• Taming Masked Diffusion Language Models via Consistency Trajectory Reinforcement Learning with Fewer Decoding Step [28.12392773921128]
  Masked diffusion language models offer properties such as parallel decoding, flexible generation orders, and the potential for fewer inference steps.<n>A naive approach is to directly transfer techniques well-established for autoregressive (AR) language models to MDLMs.<n>We propose EOS Early Rejection (EOSER) and Ascending Step-Size (ASS) decoding schedulers, which unlock the potential of MDLMs to perform full diffusion-style decoding.
  arXiv  Detail & Related papers  (2025-09-28T15:01:15Z)
• Agentic Reinforced Policy Optimization [66.96989268893932]
  Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks.<n>Current RL algorithms inadequately balance the models' intrinsic long-horizon reasoning capabilities and their proficiency in multi-turn tool interactions.<n>We propose Agentic Reinforced Policy Optimization (ARPO), a novel agentic RL algorithm tailored for training multi-turn LLM-based agents.
  arXiv  Detail & Related papers  (2025-07-26T07:53:11Z)
• MADiff: Offline Multi-agent Learning with Diffusion Models [79.18130544233794]
  MADiff is a diffusion-based multi-agent learning framework.<n>It works as both a decentralized policy and a centralized controller.<n>Our experiments demonstrate that MADiff outperforms baseline algorithms across various multi-agent learning tasks.
  arXiv  Detail & Related papers  (2023-05-27T02:14:09Z)

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.