JevGPT: Thinking Fast and Slow in Autonomous Research

cs.CL, cs.AI, cs.IR

Submitted: 2026-10-13

Updated: 2026-10-13

Comments: 24 pages, 6 figures, 7 tables. Project page: https://sunyasheng.github.io/projects/JevGPT

Project page: https://sunyasheng.github.io/projects/JevGPT

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

Sources

• MARS: Co-evolving Dual-System Deep Research via Multi-Agent Reinforcement Learning
• AtlasNav: Mitigating Evidence Blindness with Persistent Corpus Navigation
• Rethinking Agentic Search with Pi-Serini: Is Lexical Retrieval Sufficient?
• Jev-Mem: System-One-Controlled Agentic Memory for Efficient AI Agents
• NeuCLIRBench: A Modern Evaluation Collection for Monolingual, Cross-Language, and Multilingual Information Retrieval
• On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Models
• One Big Net For Everything
• SciDiagramEdit: Learning to Edit Scientific Diagrams from Paper Revisions
• Mnemon: Raw Records, Fast Judgments, Slow Thoughts
• Corrective Retrieval Augmented Generation
• Qwen3 Embedding: Advancing Text Embedding and Reranking Through Foundation Models
• Towards Retrieving Interaction Spaces for Agentic Search

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