DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation

Shuzhang Zhong; Baotong Lu; Qi Chen; Chuanjie Liu; Fan Yang; Meng Li

cs.LGMar 8, 2026

DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation

Authors: Shuzhang Zhong, Baotong Lu, Qi Chen, Chuanjie Liu, Fan Yang, Meng Li

Organizations: Peking University, Beijing, China · Microsoft Research · Microsoft

Abstract

Large language model-based deep research agents have been increasingly popular for addressing long-horizon information-seeking tasks, but they often incur high end-to-end latency due to extensive reasoning and frequent tool use. Speculation frameworks aim to reduce latency by overlapping action execution with reasoning; however, existing approaches typically rely on uniform speculation strategies and strict action matching, which limits inference speedups and robustness. In this work, we revisit the speculate-verify paradigm for deep research agents through the lens of action heterogeneity. We show that Search and Visit actions exhibit fundamentally different reasoning and model capacity requirements: entropy-based analysis reveals that Search decisions have higher uncertainty and benefit significantly from explicit reasoning, whereas Visit decisions have lower entropy and depend primarily on model capacity. Motivated by this dual-process characteristic, we propose DualSpec, a heterogeneous speculation framework equipped with a lightweight, confidence-based semantic verifier. Experiments across multiple models and benchmarks demonstrate that DualSpec achieves up to 3.28 $\times$ end-to-end speedup while maintaining accuracy comparable to fully reasoning agents.

Figures & tables

Figure 1: Deep research agent workflow. Deep research agents follow a Reason-Action-Observation loop, where the agent alternates between generating reasoning traces and executing actions (Search or Visit) to gather information.

Figure 2: Deep research inference characteristics using different models. ‘‘Miro’’ denotes ‘‘MiroThinker’’ while ‘‘Qwen’’ denotes ‘‘Qwen-3’’. (a) Tool usage ratio on the GAIA benchmark 2 2 2 Unless otherwise specified, all micro-level analyses are conducted on the GAIA benchmark; consistent trends are observed across other benchmarks. . (b) Time breakdown per step on model reasoning and tool execution. Model reasoning accounts for a significant fraction of the total latency.

Figure 3: Average reasoning length for generating Search and Visit actions across models and benchmarks. Search requires significantly longer reasoning than Visit.

Figure 4: Action alignment comparison of two speculative methods relative to the Oracle (large model with reasoning) when drafting Search and Visit. (a) The small reasoning model produces queries more aligned with the Oracle than the large model without reasoning. (b–c) For Visit, the large model skipping reasoning achieves higher accuracy in both URL selection and extraction instruction.

Configuration	MiroThinker	Qwen3
LLM with Reasoning	63.11	29.13
SLM with Reasoning for Search	63.11	29.13
LLM without Reasoning for Search	57.28	23.30
SLM without Reasoning for Search	55.34	22.33
SLM with Reasoning for Visit	56.31	22.33
LLM without Reasoning for Visit	64.08	28.16

Table 1: End-to-end agent performance (pass@1 accuracy) on GAIA under action-level replacements. We selectively replace the generation strategy for Search or Visit using lightweight methods.

Figure 5: Action log probability distributions with and without reasoning. A higher log probability indicates lower uncertainty. Without reasoning (dark blue color), Search actions exhibit lower log probabilities than Visit actions, indicating higher baseline decision uncertainty. When reasoning is incorporated (light blue color with hatching), both action types see increased log probabilities, but the increase is significantly larger for Search actions, reflecting a greater reduction in uncertainty due to reasoning.

Figure 6: Overview of DualSpec.

Figure 7: Comparison of the accuracy (pass@1) and latency of different schemes across model combinations. DualSpec consistently reduces end-to-end latency by 1.33–3.28

\times

(

\sim

\times

on average) over the base model while maintaining comparable accuracy. Compared with DSP and SPAgent, DualSpec achieves a better accuracy–latency trade-off across all datasets and model pairs.

Models	Datasets	Speculation	Acc	Lat
Miro 72B+8B	GAIA	Origin	63.1	1041
		LLM w/o Reason	59.2	575
		SLM w/ Reason	56.3	651
		Heterogeneous	63.1	605
	Xbench	Origin	66	1007
		LLM w/o Reason	65	492

Table 2: Performance under different speculation schemes.

Figure 8: Accuracy (pass@1) as a function of the reasoning intervention rate under a fixed drafting policy.

Appendix figures & tables1 asset

Supplementary material from the paper’s appendix.

Appendix

Figure 9: Verifier score distributions on GAIA and XBench-DeepResearch. We report trajectory-level aggregated verifier scores for (a) MiroThinker mean score, (b) Qwen mean score, (c) MiroThinker p25 score, and (d) Qwen p25 score. Correct trajectories consistently receive higher scores than incorrect ones, suggesting that the verifier provides a useful reliability signal.

Deep Research Agents

Deep research agents plan long-horizon searches, synthesize cited evidence, and produce reports for complex open-ended questions.

See all 115 papers

LEAP: Learning Efficient Action Proposals For LLM Agents
Oct 2, 2026Zhen Xu, Qizheng Zhang, Gerry Wan +2LLM Agents LLM Agent Training
University of Chicago · Stanford University · Together AI
AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving
Aug 1, 2026Hao Mark Chen, Jinnan Guo, Wayne Luk +1LLM Inference Acceleration Long-Horizon Agent Tasks
Imperial College London, UK
Speculate with Memory: Lossless Acceleration for LLM Agents
Jul 14, 2026Yu Li, Qinyuan Ye, Prafulla Kumar Choubey +2Next-Action Prediction LLM Agent Memory
Salesforce Research

Oct 2, 2026J/K move · Enter open · S save

LEAP: Learning Efficient Action Proposals For LLM Agents

Zhen Xu, Qizheng Zhang, Gerry Wan, Shang Zhu+1

University of Chicago · Stanford University · Together AI

LLM Agents LLM Agent Training

Open paper AskPDF arXiv

LLM agents are known to be slow in rollouts. An agent completes a task one step at a time. At each step, it reasons and then chooses an action to execute. The next step and action cannot start until the previous one has finished. Speculative decoding accelerates the rollouts at the reason phase by drafting and verifying the inference tokens. Recent works have also started to apply similar ideas at the action phase. These works use off-the-shelf models, usually large, to draft action proposals for target model to verify. Large drafters match the target more often but take longer to propose, while small off-the-shelf models are fast but rarely make the same decision as the target. We ask a more general question: what determines the end-to-end speedup of action speculation? To answer it, we develop a latency framework for the speculative round. The framework compares what a round gains with what it costs. The gain depends on how well the drafter predicts the target and on how many steps the task can take before it ends. The cost comes from drafting, from waiting for target verification and from executing tools. Guided by the framework, we introduce LEAP (Learning Efficient Action Proposals) which keeps the drafter small and makes it accurate by training it on the target actions sequences. With a small 0.6B model, LEAP agrees with the target on most decisions and makes agents up to 60% faster in end-to-end wall clock time, with no systematic change in task success. Across various datasets, target models and draft models, the framework accounts for most of the measured speedups. We also show the draft model can be online trained with no prior trace collection and match the performance of offline training, making LEAP practical to deploy in the real world.

Abstract

Deep Research Agents

Explore similar work

LEAP: Learning Efficient Action Proposals For LLM Agents

AOSpec: Action and Observation Co-Speculation for Low-Latency Agent Serving

Speculate with Memory: Lossless Acceleration for LLM Agents