analiza aiqbench
This research introduces TAEC, a training-free framework that optimizes evidence utilization in multi-step visual retrieval-augmented generation by dynamically coordinating context based on unresolved reasoning requirements. By filtering redundant sources and managing memory retention throughout the trajectory, the method significantly improves accuracy across proprietary vision-language models without requiring additional training. The work directly addresses critical bottlenecks in long-context visual reasoning, offering a practical path to more efficient and accurate complex document analysis systems.
TAEC: Trajectory-Aware Evidence Coordination for Multi-Step Visual RAG
arXiv:2609.37349v1 Announce Type: cross Abstract: Multi-step visual retrieval-augmented generation (RAG) answers complex questions by repeatedly retrieving visual evidence, updating an intermediate state, and deciding whether to continue searching or answer. Yet retrieving relevant evidence does not ensure its effective use throughout the reasoning trajectory. As multi-step reasoning progresses, redundant sources occupy context capacity needed for missing evidence, observations tied to resolved requirements or unproductive searches linger in context, and visual sources are revisited with insufficient detail for fine-grained reading. We term this loss of usable evidence over a reasoning trajectory trajectory-level evidence utilization degradation. To address it, we propose Trajectory-Aware Evidence Coordination (TAEC), a training-free framework that coordinates evidence use around unresolved answer requirements. TAEC tracks these requirements in a shared trajectory state to guide which evidence enters the context, how accumulated memory is retained, and at what level of detail visual evidence is examined. Under a unified evaluation protocol on ViDoSeek, SlideVQA, and MMLongBench-Doc, TAEC achieves the best overall performance against leading training-free visual RAG baselines, with the highest average accuracy across multiple proprietary vision-language models. These results demonstrate that aligning evidence with evolving reasoning needs improves evidence use throughout multi-step visual RAG.
Abstract:Multi-step visual retrieval-augmented generation (RAG) answers complex questions by repeatedly retrieving visual evidence, updating an intermediate state, and deciding whether to continue searching or answer. Yet retrieving relevant evidence does not ensure its effective use throughout the reasoning trajectory. As multi-step reasoning progresses, redundant sources occupy context capacity needed for missing evidence, observations tied to resolved requirements or unproductive searches linger in context, and visual sources are revisited with insufficient detail for fine-grained reading. We term this loss of usable evidence over a reasoning trajectory trajectory-level evidence utilization degradation. To address it, we propose Trajectory-Aware Evidence Coordination (TAEC), a training-free framework that coordinates evidence use around unresolved answer requirements. TAEC tracks these requirements in a shared trajectory state to guide which evidence enters the context, how accumulated memory is retained, and at what level of detail visual evidence is examined. Under a unified evaluation protocol on ViDoSeek, SlideVQA, and MMLongBench-Doc, TAEC achieves the best overall performance against leading training-free visual RAG baselines, with the highest average accuracy across multiple proprietary vision-language models. These results demonstrate that aligning evidence with evolving reasoning needs improves evidence use throughout multi-step visual RAG.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.37349 [cs.CV]
(or arXiv:2609.37349v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.37349 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 289 cuvinte
Subiecte conexe
[AINews] not much happened today
Latent Space · 10 sept. 2026
Why do models task game?
AI Alignment Forum · 6 aug. 2026
[AINews] High Taste Testers Ep. 1
Latent Space · 17 oct. 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · 26 aug. 2026