Task-Adaptive Retrieval over Agentic Multi-Modal Web Histories via Learned Graph Memory

2026-04-09 · Saman Forouzandeh, Kamal Berahmand, Mahdi Jalili arxiv

Retrieving relevant observations from long multi-modal web interaction histories is challenging because relevance depends on the evolving task state, modality (screenshots, HTML text, structured signals), and temporal distance. Prior approaches typically rely on static similarity thresholds or fixed-capacity buffers, which fail to adapt relevance to the current task context. We propose \textbf{ACGM}, a learned graph-memory retriever that constructs \emph{task-adaptive} relevance graphs over agent histories using policy-gradient optimization from downstream task success. ACGM captures heterogeneous temporal dynamics with modality-specific decay (visual decays $4.3\times$ faster than text: $λ_v{=}0.47$ vs.\ $λ_x{=}0.11$) and learns sparse connectivity (3.2 edges/node), enabling efficient $O(\log T)$ retrieval. Across WebShop, VisualWebArena, and Mind2Web, ACGM improves retrieval quality to \textbf{82.7 nDCG@10} (+9.3 over GPT-4o, $p{<}0.001$) and \textbf{89.2\% Precision@10} (+7.7), outperforming 19 strong dense, re-ranking, multi-modal, and graph-based baselines. Code to reproduce our results is available at{\color{blue}\href{https://github.com/S-Forouzandeh/ACGM-Agentic-Web}{Saman Forouzandeh}}.

📄 PDF Abstract BibTeX arXiv:2604.07863

Code (0)

등록된 구현이 없습니다.

Dissecting Agentic RAG: A Component Ablation for Multi-Hop QA with a Local 7B Model

2026-06-19 · Sheroz Shaikh arxiv

Agentic retrieval-augmented generation (RAG) systems combine iterative reasoning loops, query decomposition, and adaptive retrieval to tackle multi-hop question answering. However, the contribution of each component rema…

Multi-hop Question Answering

A2RAG: Adaptive Agentic Graph Retrieval for Cost-Aware and Reliable Reasoning

2026-01-29 · Jiate Liu, Zebin Chen, Shaobo Qiao, Mingchen Ju 외 arxiv

Graph Retrieval-Augmented Generation (Graph-RAG) enhances multihop question answering by organizing corpora into knowledge graphs and routing evidence through relational structure. However, practical deployments face two…

Question Answering Knowledge Graphs

Reasoning RAG via System 1 or System 2: A Survey on Reasoning Agentic Retrieval-Augmented Generation for Industry Challenges

2025-06-12 · Jintao Liang, Gang Su, Huifeng Lin, You Wu 외

Retrieval-Augmented Generation (RAG) has emerged as a powerful framework to overcome the knowledge limitations of Large Language Models (LLMs) by integrating external retrieval with language generation. While early RAG s…

Decision Making RAG Retrieval Retrieval-augmented Generation+1

DynaTree: Dynamic Agentic Retrieval Tree for Time-Sensitive News Retrieval

2026-05-29 · Siyuan Qi, Xinyuan Wang, Yingxuan Yang, Haochuan Guo 외 arxiv

Agentic Retrieval-Augmented Generation improves retrieval by integrating planning, tool use, and iterative reasoning, but existing agentic RAG methods often couple semantic expansion with retrieval decisions in short-hor…

MAGMA: A Multi-Graph based Agentic Memory Architecture for AI Agents

2026-01-06 · Dongming Jiang, Yi Li, Guanpeng Li, Bingzhe Li arxiv

Memory-Augmented Generation (MAG) extends Large Language Models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entanglin…

Semantic Similarity