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

• URL: http://arxiv.org/abs/2603.07416v1
• Date: Sun, 08 Mar 2026 02:03:58 GMT
• Title: DualSpec: Accelerating Deep Research Agents via Dual-Process Action Speculation
• Abstract summary: Speculation frameworks aim to reduce latency by overlapping action execution with reasoning.<n>Existing approaches typically rely on uniform speculation strategies and strict action matching.<n>We propose DualSpec, a heterogeneous speculation framework equipped with a lightweight, confidence-based semantic verifier.
• Score: 10.076688905947103
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• 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 \textit{Search} and \textit{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.

Related papers

• DR-MMSearchAgent: Deepening Reasoning in Multimodal Search Agents [24.61813749877376]
  Deepening Reasoning MMSearchAgent derives advantage signals from whole rollout trajectories in an entire batch.<n> differentiated gaussian rewards are employed to dynamically calibrate interaction tolerance.<n>Our method achieves state-of-the-art performance, outperforming the MMSearch-R1 by 8.4$%$ on FVQA-test.
  arXiv  Detail & Related papers  (2026-04-21T09:28:34Z)
• Efficient Test-Time Scaling via Temporal Reasoning Aggregation [5.87118425760756]
  We propose TRACE, a training-free framework for efficient test-time scaling.<n>TRACE determines when to terminate reasoning based on temporal aggregation of multi-step evidence.<n>We show that TRACE reduces reasoning token usage by 25-30% on average while maintaining accuracy within 1-2% of full-length reasoning.
  arXiv  Detail & Related papers  (2026-04-19T07:39:40Z)
• Think Longer to Explore Deeper: Learn to Explore In-Context via Length-Incentivized Reinforcement Learning [53.58654277639939]
  In-context exploration is the intrinsic ability to generate, verify, and refine hypotheses within a single continuous context.<n>We propose Length-Incentivized Exploration, which explicitly encourages models to explore more.<n>Our method achieves an average improvement of 4.4% on in-domain tasks and a 2.7% gain on out-of-domain benchmarks.
  arXiv  Detail & Related papers  (2026-02-12T09:24:32Z)
• Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration [49.9937230730202]
  We propose Search-R2, a novel Actor-Refiner collaboration framework that enhances reasoning through targeted intervention.<n>Our approach decomposes the generation process into an Actor, which produces initial reasoning trajectories.<n>We show that Search-R2 consistently outperforms strong RAG and RL-based baselines across model scales.
  arXiv  Detail & Related papers  (2026-02-03T15:32:09Z)
• ConfSpec: Efficient Step-Level Speculative Reasoning via Confidence-Gated Verification [0.2578242050187029]
  Step-level speculative reasoning aims to mitigate this cost, yet existing approaches face a long-standing trade-off.<n>We propose ConfSpec, a confidence-gated cascaded verification framework that resolves this trade-off.
  arXiv  Detail & Related papers  (2026-01-28T05:58:05Z)
• Adversarial Yet Cooperative: Multi-Perspective Reasoning in Retrieved-Augmented Language Models [72.4149653187766]
  We propose a Reasoner-Verifier framework named Adrialversa Reasoning RAG (ARR)<n>The Reasoner and Verifier engage in reasoning on retrieved evidence and critiquing each other's logic while being guided by process-aware advantage.<n> Experiments on multiple benchmarks demonstrate the effectiveness of our method.
  arXiv  Detail & Related papers  (2026-01-08T06:57:03Z)
• Reducing Latency of LLM Search Agent via Speculation-based Algorithm-System Co-Design [35.95362310928356]
  LLM-based search agents achieve strong performance but suffer from severe latency.<n>We revisit this bottleneck through the lens of speculation.<n>We present SPAgent, an algorithm-system co-design framework that expands the role of speculation in search agents to reduce latency.
  arXiv  Detail & Related papers  (2025-11-25T08:15:17Z)
• ParallelMuse: Agentic Parallel Thinking for Deep Information Seeking [59.65564262588308]
  Parallel thinking expands exploration breadth, complementing the deep exploration of information-seeking (IS) agents.<n>We propose ParallelMuse, a two-stage paradigm designed for deep IS agents.<n> Experiments across multiple open-source agents and benchmarks demonstrate up to 62% performance improvement.
  arXiv  Detail & Related papers  (2025-10-28T17:51:50Z)
• Demystifying deep search: a holistic evaluation with hint-free multi-hop questions and factorised metrics [89.1999907891494]
  We present WebDetective, a benchmark of hint-free multi-hop questions paired with a controlled Wikipedia sandbox.<n>Our evaluation of 25 state-of-the-art models reveals systematic weaknesses across all architectures.<n>We develop an agentic workflow, EvidenceLoop, that explicitly targets the challenges our benchmark identifies.
  arXiv  Detail & Related papers  (2025-10-01T07:59:03Z)
• Accelerating Large Language Model Reasoning via Speculative Search [59.48276891032373]
  We propose a novel Speculative Search (SpecSearch) framework that significantly accelerates large language models (LLMs) reasoning.<n>Specifically, SpecSearch utilizes a small model to strategically collaborate with a large model at both thought and token levels.<n>The major pillar of SpecSearch is a novel quality-preserving rejection mechanism, which effectively filters out thoughts whose quality falls below that of the large model's outputs.
  arXiv  Detail & Related papers  (2025-05-03T12:14:08Z)

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.