DLLM-Searcher: 为搜索代理适应扩散大语言模型
DLLM-Searcher: Adapting Diffusion Large Language Model for Search Agents
AI总结：
DLLM-Searcher通过优化基于dLLM的搜索代理，解决代理能力不足和延迟挑战，提升推理效率。
摘要：
最近，扩散大语言模型（dLLMs）已展现出独特的效率优势，这得益于其内在并行解码机制和灵活的生成范式。同时，尽管搜索代理的进步迅速，但其实际部署受到一个根本性的限制，称为1）延迟挑战：在ReAct代理范式下，多轮推理、工具调用和工具响应等待的串行执行导致严重的端到端延迟。直观上，dLLMs可以利用其独特的优势来优化ReAct代理范式下的代理操作效率。实际上，现有的dLLM骨干面临2）代理能力挑战。也就是说，现有的dLLMs表现出显著的推理和工具调用能力薄弱，阻碍了这些优势在实际中的有效实现。在本文中，我们提出了DLLM-Searcher，一种为基于dLLM的搜索代理优化的框架。为解决代理能力挑战，我们设计了一个两阶段的后训练管道，包括代理监督微调（Agentic SFT）和代理方差减少偏好优化代理Agentic VRPO，这增强了dLLM骨干的信息搜索和推理能力。为缓解延迟挑战，我们利用dLLM的灵活生成机制，并提出了一种新的代理范式，称为并行推理和行动P-ReAct。P-ReAct指导模型优先解码工具调用指令，从而允许模型在等待工具返回时继续思考。实验结果表明，DLLM-Searcher的性能与主流基于LLM的搜索代理相当，P-ReAct提供了约15%的推理加速。我们的代码可在https://anonymous.4open.science/r/DLLM-Searcher-553C获取。
英文摘要：
Recently, Diffusion Large Language Models (dLLMs) have demonstrated unique efficiency advantages, enabled by their inherently parallel decoding mechanism and flexible generation paradigm. Meanwhile, despite the rapid advancement of Search Agents, their practical deployment is constrained by a fundamental limitation, termed as 1) Latency Challenge: the serial execution of multi-round reasoning, tool calling, and tool response waiting under the ReAct agent paradigm induces severe end-to-end latency. Intuitively, dLLMs can leverage their distinctive strengths to optimize the operational efficiency of agents under the ReAct agent paradigm. Practically, existing dLLM backbones face the 2) Agent Ability Challenge. That is, existing dLLMs exhibit remarkably weak reasoning and tool-calling capabilities, preventing these advantages from being effectively realized in practice. In this paper, we propose DLLM-Searcher, an optimization framework for dLLM-based Search Agents. To solve the Agent Ability Challenge, we design a two-stage post-training pipeline encompassing Agentic Supervised Fine-Tuning (Agentic SFT) and Agentic Variance-Reduced Preference Optimization Agentic VRPO, which enhances the backbone dLLM's information seeking and reasoning capabilities. To mitigate the Latency Challenge, we leverage the flexible generation mechanism of dLLMs and propose a novel agent paradigm termed Parallel-Reasoning and Acting P-ReAct. P-ReAct guides the model to prioritize decoding tool_call instructions, thereby allowing the model to keep thinking while waiting for the tool's return. Experimental results demonstrate that DLLM-Searcher achieves performance comparable to mainstream LLM-based search agents and P-ReAct delivers approximately 15% inference acceleration. Our code is available at https://anonymous.4open.science/r/DLLM-Searcher-553C
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
