Agent-FLAN: Designing Data and Methods of Effective Agent Tuning for Large Language Models (2024 · 64 citations)
Open-source LLMs still perform much worse than API-based systems such as GPT-4 when used as agents. Tuning them on agent-specific data can also weaken their general skills. The authors make three diagnostic observations:
ViDoRAG: Visual Document Retrieval-Augmented Generation via Dynamic Iterative Reasoning Agents (2025 · 39 citations)
The paper addresses retrieval-augmented generation (RAG) over large collections of visually rich documents such as slides with charts, tables and diagrams.
VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning (2025 · 23 citations)
Answering questions over visually rich documents such as slides, reports, charts and tables is difficult for standard RAG.
MindSearch: Mimicking Human Minds Elicits Deep AI Searcher (2024 · 20 citations)
Pairing LLMs with web search often fails on complex questions. A single retrieval pass rarely covers everything the question needs. Relevant facts are scattered across many noisy pages, and the combined page text quickly exceeds the model's context window. MindSearch addresses this with a two-role multi-agent design…

Co-authors here

12 of 13 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 112 times (of the 149,439 papers whose bibliographies we read); 30 citing papers with a page here →.

Updated 30 October 2026