AWM: Answerable Working Memory for Long-Document VQA Agents

arXiv:2608.25618 · cs.CL · Submitted 2026-08-26 · Read on arXiv

cs.CL

Submitted: 2026-08-26

Updated: 2026-08-26

Comments: EMNLP 2026 Findings. 16 pages, 4 figures, 9 tables

Code: https://github.com/DongzhuoranZhou/AWM

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• GRPO — 84× in this paper · explained in 6 episodes
• Accuracy — 33× in this paper · explained in 1 episode
• RAG — 31× in this paper · explained in 3 episodes
• Benchmark — 20× in this paper · explained in 2 episodes
• Grounding — 11× in this paper · explained in 3 episodes
• Knowledge Graph — 6× in this paper · explained in 7 episodes
• Reinforcement Learning — 6× in this paper · explained in 4 episodes
• Agent Memory — 4× in this paper · explained in 1 episode
• Answerable Working Memory — 4× in this paper
• Embeddings — 4× in this paper · explained in 2 episodes
• Verification — 3× in this paper · explained in 2 episodes
• AgenticRAG-R1 — 2× in this paper · explained in 1 episode
• Alignment — 2× in this paper · explained in 1 episode
• Benchmarking — 2× in this paper · explained in 3 episodes
• Robustness — 2× in this paper · explained in 5 episodes
• Trace — 2× in this paper · explained in 2 episodes
• Adam — 1× in this paper · explained in 2 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Adaptive Graph — 1× in this paper · explained in 1 episode
• Agentic System — 1× in this paper · explained in 2 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Interpretability — 1× in this paper · explained in 15 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Multimodal Reasoning — 1× in this paper · explained in 5 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Self-consistency — 1× in this paper · explained in 2 episodes
• Verifiability — 1× in this paper · explained in 2 episodes
• Verifiable Rewards — 1× in this paper · explained in 2 episodes

Sources

• SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding
• M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding
• Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models
• MM-Doc-R1: Training Agents for Long Document Visual Question Answering through Multi-turn Reinforcement Learning
• Auditing Data Membership in Reinforcement Learning With Verifiable Rewards
• VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning
• Staying VIGILant: Mitigating Visual Laziness via Counterfactual Visual Alignment in MLLMs
• EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
• MemSearcher: Training LLMs to Reason, Search and Manage Memory via End-to-End Reinforcement Learning
• Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
• Evaluating Knowledge Graph Based Retrieval Augmented Generation Methods under Knowledge Incompleteness
• GR-Agent: Adaptive Graph Reasoning Agent under Incomplete Knowledge
• Look Inward to Explore Outward: Learning Temperature Policy from LLM Internal States via Hierarchical RL
• Conformalized Large Language Models under Configuration Shift

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering