Data to 14 Oct 2026

JevGPT: Thinking Fast and Slow in Autonomous Research

arXiv 2610.18272 ↗First posted 13 Oct 2026cs.CL cs.AI cs.IRcited by 0

On the map: LLM agents and tool use → Web, search, and research agents

Abstract (arXiv)

Autonomous research agents must acquire and reason over evidence within a limited budget. Yet relevant sources can remain uninspected or unused, leaving a gap between retrieval coverage and the evidence that informs research. The challenge is to align fast local judgments with changing evidence needs and feed their findings back into research decisions. We introduce JevGPT, a dual-system architecture for autonomous research that couples fast evidence processing with deliberative research planning. System Two sets evidence objectives and integrates findings, while System One locates support, assesses relevance, and guides further inspection. Independent source judgments run in parallel; selected original passages inform the next research step. Experiments on fixed-corpus question answering and document ranking show that JevGPT achieves leading task performance, with faster completion and lower cost than comparably effective research agents. Evidence analysis shows broader source inspection and greater coverage of supporting documents in the research loop, highlighting efficient evidence processing as a route to more capable autonomous research.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use. Builds on 22 of its 34 references that are in the map. First posted on arXiv 13 Oct 2026.

Builds on

22 of 34 references.

Closest ancestors · 2

Same direction, newest first

Other references · 20

2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
2023Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflectioncited by 1,839
2025Search-R1: Training LLMs to Reason and Leverage Search Engines with Reinforcement Learningcited by 1,444
2025Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Modelscited by 1,261
2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 923
2023FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performancecited by 853
2023SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Taskscited by 168
2019Deeper Text Understanding for IR with Contextual Neural Language Modelingcited by 113
2015On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Modelscited by 55
2022An Analysis of Fusion Functions for Hybrid Retrievalcited by 51
2018One Big Net For Everythingcited by 16

8 more

2025Beyond Outlining: Heterogeneous Recursive Planning for Adaptive Long-form Writing with Language Modelscited by 16
2025RankLLM: A Python Package for Reranking with LLMscited by 16
2026Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agentscited by 14
2024AVI-Talking: Learning Audio-Visual Instructions for Expressive 3D Talking Face Generationcited by 9
2025NeuCLIRBench: A Modern Evaluation Collection for Monolingual, Cross-Language, and Multilingual Information Retrievalcited by 7
2022Patapasco: A Python Framework for Cross-Language Information Retrieval Experimentscited by 5
2026SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisionscited by 2
2026Mnemon: Raw Records, Fast Judgments, Slow Thoughtscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way