DocMemo: Probabilistic Memory-Guided Retrieval Framework for Multi-Modal Long Documents
_reachsumit · x · 2026-08-10
Long-document understanding requires locating sparse and heterogeneous evidence across hundreds of pages, but existing systems are limited by static retrieval and fragile cross-round memory. To address this, the paper introduces DocMemo, a framework formulating long-document reasoning as dynamic evidence exploration.
DocMemo maintains a tri-level retrieval state memory: Document Schema Memory, Page Belief Memory, and Question Episodic Memory. During reasoning, it continuously refines cross-round page selection through Bayesian page belief updating with Thompson sampling, spatial proximity propagation, and structure-aware adaptive-granularity evidence access. Experiments show that DocMemo achieves state-of-the-art performance on three benchmarks.
More from Research
- Peking University releases OmniEdu, open education foundation models in 4B/9B/27B sizes — PekingUniversity · 2026-09-22
- VR mocap pipeline captures 1,185 human trajectories to teach Unitree G1 to navigate clutter — Scobleizer · 2026-09-22
- AI memory system built with Jev claims 10x speed, 6x lower cost — realferrari · 2026-09-22
- AF3-style confidence heads surprisingly insensitive to diffusion module coordinates — chaitjo · 2026-09-22
- riderless: A Zero-Token Decision API on Gemma 4 Hits 93.1% Accuracy on One RTX 5090 — Pale-Soil-2524 · 2026-09-22
- Shenzhen University and HKUST propose ECA: evidence checks before agent actions — jiqizhixin · 2026-09-22