SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

• URL: http://arxiv.org/abs/2603.23483v1
• Date: Tue, 24 Mar 2026 17:45:47 GMT
• Title: SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning
• Abstract summary: Agentic multimodal large language models (MLLMs) achieve remarkable reasoning capabilities through iterative visual tool invocation.<n>However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead.<n>This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level throughput.<n>We propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck.
• Score: 104.01865949020304
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Agentic multimodal large language models (MLLMs) (e.g., OpenAI o3 and Gemini Agentic Vision) achieve remarkable reasoning capabilities through iterative visual tool invocation. However, the cascaded perception, reasoning, and tool-calling loops introduce significant sequential overhead. This overhead, termed agentic depth, incurs prohibitive latency and seriously limits system-level concurrency. To this end, we propose SpecEyes, an agentic-level speculative acceleration framework that breaks this sequential bottleneck. Our key insight is that a lightweight, tool-free MLLM can serve as a speculative planner to predict the execution trajectory, enabling early termination of expensive tool chains without sacrificing accuracy. To regulate this speculative planning, we introduce a cognitive gating mechanism based on answer separability, which quantifies the model's confidence for self-verification without requiring oracle labels. Furthermore, we design a heterogeneous parallel funnel that exploits the stateless concurrency of the small model to mask the stateful serial execution of the large model, maximizing system throughput. Extensive experiments on V* Bench, HR-Bench, and POPE demonstrate that SpecEyes achieves 1.1-3.35x speedup over the agentic baseline while preserving or even improving accuracy (up to +6.7%), thereby boosting serving throughput under concurrent workloads.

Related papers

• Unlocking Complex Visual Generation via Closed-Loop Verified Reasoning [11.461705552241163]
  Closed-Loop Visual Reasoning (CLVR) is a comprehensive system that couples visual-language logical planning with pixel-level diffusion generation.<n> CLVR introduces an automated data engine with step-level visual verification to synthesize reliable reasoning trajectories.<n>To mitigate the severe latency bottleneck caused by iterative denoising, we propose $$-Space Weight (DSWM)
  arXiv  Detail & Related papers  (2026-05-14T14:22:25Z)
• GRAIL: A Deep-Granularity Hybrid Resonance Framework for Real-Time Agent Discovery via SLM-Enhanced Indexing [0.0]
  textbfGRAIL (Granular Resonance-based Agent/AI Link) is a novel framework achieving sub-400ms discovery latency without compromising accuracy.<n>GRAIL reduces end-to-end discovery latency by over textbf79$times compared to LLM-parsing baselines, while significantly outperforming traditional vector search in Recall@10.
  arXiv  Detail & Related papers  (2026-05-04T11:41:45Z)
• Waking Up Blind: Cold-Start Optimization of Supervision-Free Agentic Trajectories for Grounded Visual Perception [18.565166776233223]
  Small Vision-Language Models (SVLMs) are efficient task controllers but often suffer from visual brittleness and poor tool orchestration.<n>We propose Self-supervised Perception Enabled by Cascaded Tool Rollout Alignment (SPECTRA)<n>SPECTRA bootstraps agentic capabilities via Coldstart Reinforcement Learning for SVLMs.
  arXiv  Detail & Related papers  (2026-04-19T15:06:30Z)
• Refer-Agent: A Collaborative Multi-Agent System with Reasoning and Reflection for Referring Video Object Segmentation [50.22481337087162]
  Referring Video Object (RVOS) aims to segment objects in videos based on textual queries.<n>Refer-Agent is a collaborative multi-agent system with alternating reasoning-reflection mechanisms.
  arXiv  Detail & Related papers  (2026-02-03T14:48:12Z)
• 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)
• HALO: Semantic-Aware Distributed LLM Inference in Lossy Edge Network [50.33808558714122]
  Large language models' (LLMs) inference at the edge can facilitate prompt service responsiveness while protecting user privacy.<n>We propose HALO, a novel framework that can boost the distributed LLM inference in lossy edge network.<n> Experimental results from a Raspberry Pi cluster demonstrate that HALO achieves a 3.41x end-to-end speedup for LLaMA-series LLMs under unreliable network conditions.
  arXiv  Detail & Related papers  (2026-01-16T07:37:23Z)
• Towards Efficient Agents: A Co-Design of Inference Architecture and System [66.59916327634639]
  This paper presents AgentInfer, a unified framework for end-to-end agent acceleration.<n>We decompose the problem into four synergistic components: AgentCollab, AgentSched, AgentSAM, and AgentCompress.<n>Experiments on the BrowseComp-zh and DeepDiver benchmarks demonstrate that through the synergistic collaboration of these methods, AgentInfer reduces ineffective token consumption by over 50%.
  arXiv  Detail & Related papers  (2025-12-20T12:06:13Z)
• Scaling LLM Speculative Decoding: Non-Autoregressive Forecasting in Large-Batch Scenarios [76.85739138203014]
  We present SpecFormer, a novel architecture that accelerates unidirectional and attention mechanisms.<n>We demonstrate that SpecFormer achieves lower training demands and reduced computational costs.
  arXiv  Detail & Related papers  (2025-11-25T14:20:08Z)
• 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)
• Mirror Speculative Decoding: Breaking the Serial Barrier in LLM Inference [11.957170239588535]
  Speculative decoding accelerates inference by using a draft model to look ahead.<n>Prior methods partially reduce draft cost but either degrade acceptance or introduce overheads that limit scaling.<n>We present Mirror Speculative Decoding (Mirror-SD), an inference algorithm that breaks the latency-acceptance tradeoff.
  arXiv  Detail & Related papers  (2025-10-15T05:22:57Z)
• ReAgent-V: A Reward-Driven Multi-Agent Framework for Video Understanding [71.654781631463]
  ReAgent-V is a novel agentic video understanding framework.<n>It integrates efficient frame selection with real-time reward generation during inference.<n>Extensive experiments on 12 datasets demonstrate significant gains in generalization and reasoning.
  arXiv  Detail & Related papers  (2025-06-02T04:23:21Z)
• SpecEE: Accelerating Large Language Model Inference with Speculative Early Exiting [12.317709090608837]
  We present SpecEE, a fast inference engine with speculative early exiting.<n>SpecEE achieves 2.25x and 2.43x speedup with Llama2-7B on cloud and PC scenarios respectively.
  arXiv  Detail & Related papers  (2025-04-11T02:38:53Z)
• TurboSpec: Closed-loop Speculation Control System for Optimizing LLM Serving Goodput [37.56866491624234]
  Large Language Model (LLM) serving systems batch concurrent user requests to achieve efficient serving.<n>We present TurboSpec, a speculation control system that automatically profiles the execution environment.<n>We demonstrate its effectiveness across diverse workloads and hardware configurations.
  arXiv  Detail & Related papers  (2024-06-20T07:43:33Z)

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.