Autonomous Experimentation

Follow this topic Ask about this topic

Momentum

15 papers in the last four weeks, up 114% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 95

All topics

LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models
Oct 8, 2026Surya Shetty, Ulisses Braga-NetoAutonomous Scientific Discovery Autonomous Experimentation
Texas A&M University · Polara Labs Inc.
RSIGym: A Flexible Environment for Recursive Self-Improvement
Oct 7, 2026Fanqing Meng, Lingxiao Du, Haocheng Lu +6LLM Agent Self-Improvement Recursive Self-Improvement
Evolvent AI · National University of Singapore
Fork-and-Flush: Escaping Idea Basins in Autoresearch Agents
Oct 5, 2026Ziyang Cai, Christos Ziakas, Vasilis Kontonis +5Local Search Long-Horizon Agent Tasks
Microsoft Research
MECHVAR: Variance-Guided Mechanism Discrimination for Autonomous Machine Learning Experiment Selection
Oct 1, 2026Yifan GuoBayesian Experimental Design Autonomous Experimentation
Stony Brook University
AbsorbEvo: An Agentic Framework for Autonomous Inverse Design of Microwave Absorbers
Oct 1, 2026Zhicheng Feng, Yubo Zhao, Xuefeng YaoLarge Language Model-Guided Optimization Natural Language to Optimization Modeling
Department of Engineering Mechanics, Applied Mechanics Lab, Tsinghua University, Beijing 100084, P. R. China
Experimental Experience Modeling for Autonomous Research
Sep 30, 2026Wenda Wei, Yingchen Zhang, Ruqing Zhang +3AI Agents for Scientific Discovery Autonomous Experimentation
State Key Laboratory of AI Safety · Institute of Computing Technology, Chinese Academy of Sciences · University of Chinese Academy of Sciences +1
Autoresearch in Mixed-Integer Linear and Nonlinear Programming
Sep 30, 2026Yuwei Gu, Yaoxin Wu, Tong Guo +2Automated Algorithm Discovery Mixed-Integer Linear Programming
Chengdu University of Information Technology · Eindhoven University of Technology · Nanyang University of Technology +2
SimEX: Simulation-Integrated Robotics AutoResearch
Sep 30, 2026Jiaheng Hu, Roberto Martin-Martin, Peter Stone +3Robot Skill Learning Robotics Simulation
Amazon FAR (Frontier AI & Robotics) · The University of Texas at Austin · Carnegie Mellon University
RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement
Sep 28, 2026Yaxin Du, Xiyuan Yang, Zhifan Zhou +10Language Model Post-Training Self-Improving Agents
Shanghai Jiao Tong University · Carnegie Mellon University · University of Waterloo
PEAR: Progressive Evidence-Based AutoResearch for Industrial Search Systems
Sep 28, 2026Yifan Wang, Shipeng Zhu, Fei Xiong +6Information Retrieval Sequential Hypothesis Testing
Global E-Commerce Agentic Search Team
ALDER: Discovering the Laws of a World by Acting in It
Sep 27, 2026Teng Cao, Yu Deng, Quentin Delfosse +1Scientific Discovery Action-Conditioned World Models
Technische Universität Darmstadt · Intrinsic · CS Department, TU Darmstadt +2
Advancing Model Research in AgentX: Long-Horizon Autonomy for Industrial Recommender Systems
Sep 24, 2026Shuang Yang, Zijie Zhuang, Changxin Lao +20AI Agents for Scientific Discovery Long-Horizon Agent Evaluation
WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents
Sep 23, 2026Jingjie Ning, Xueqi Li, Yibo Kong +1AI Agent Evaluation Active Learning
Carnegie Mellon University · Tsinghua University
Evidence-Grounded Agentic Formulation Development in an Autonomous Laboratory
Sep 16, 2026Michael M. Craig, Riley J. Hickman, Yingshan Ma +3Autonomous Experimentation Autonomous Research Agents
Intrepid Labs, Toronto, Canada
Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents
Sep 16, 2026Izumi Takahara, Kazunori Nishio, Akira Aiba +4LLM Agent Skill Learning Autonomous Scientific Discovery
Institute of Industrial Science, The University of Tokyo, Tokyo 153-8505, Japan · Department of Chemistry, The University of Tokyo, Tokyo 113-0033, Japan · Rigaku Corporation, Tokyo 196-8666, Japan +1
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Sep 14, 2026Tong Zheng, Xidong Wu, Zheng Zhang +14RL Exploration Self-Improving Agents
Google · University of Maryland, College Park · Google Deepmind +1
Auto-RecSys: Harnessing Autonomous Research Agents for Industry-Scale Recommender System
Sep 11, 2026Ming Li, Dai Li, Xuying Ning +11Recommender Systems Long-Horizon LLM Agents
Meta · University of Illinois Urbana-Champaign
La Agente 'Optima: Towards Agentic Self-Driving Laboratories
Sep 7, 2026Marcel Müller, Jiaru Bai, Willi Gottstein +14Bayesian Optimization Large Language Model-Guided Optimization
Department of Chemistry, University of Toronto, 80 St. George St., Toronto, ON M5S 3H6, Canada · Vector Institute for Artificial Intelligence, W1140-108 College St., Schwartz Reisman Innovation Campus, Toronto, ON2026 M5G 0C6, Canada · Acceleration Consortium, 700 University Ave., Toronto, ON M7A 2S4, Canada +11
Science sandboxes measure the scientific capability of AI agents
Aug 31, 2026Arya S. Rao, Rodrigo I. Castro, Sager J. Gosai +8Protein Fitness Prediction AI Agent Evaluation
The Broad Institute of MIT and Harvard; Cambridge, MA 02142, USA. · Department of Biomedical Informatics, Harvard Medical School; Boston, MA 02115, USA. · The Jackson Laboratory; Bar Harbor, ME 04609, USA. +10
AutoResearch: Insight In, Hallucination Out
Aug 18, 2026Xiang Liu, Qumeng Sun, Bruno +3Scientific Hypothesis Generation Research Idea Generation
Infinite Evolution Lab, EvoMap
AQuA: Recursively Self-Improving Quantitative Trading Research Agents
Aug 13, 2026Jiacheng Guo, Suozhi Huang, Yunlong Gao +5Quantitative Finance Automated Algorithm Discovery
Princeton University · Ant Group · Stanford University
ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation
Aug 11, 2026Jiangjie Qiu, Yijun Li, Xiaonan WangAI Agents for Scientific Discovery Scientific Reproducibility
Beijing Key Laboratory of Artificial Intelligence for Advanced Chemical Engineering Materials, State Key Laboratory of Chemical Engineering and Low-Carbon Technology, Department of Chemical Engineering, Tsinghua University, Beijing 100084, China
Agentic Auto-Research is Fuzz Testing
Aug 10, 2026Yifeng He, Jicheng Wang, Yinzhe Zhao +2AI Agents for Scientific Discovery Autonomous Experimentation
University of California, Davis · ARA Lab · Zhejiang University +2
Multitask Scanning Probe Microscopy
Aug 10, 2026Aditya Raghavan, Yu Liu, Ian Mercer +2Active Learning Multi-Task Learning
University of Tennessee, Knoxville, TN, USA · 2Pennsylvania State University, University Park, PA, USA
Causal Behavioral Evaluation of AI Agents at Scale via Automated Behavioral Science
Aug 10, 2026Soo Yong Lee, Jongha Lee, Jaewan Chun +8AI-Assisted Scientific Research AI Agent Evaluation
KAIST, Kim Jaechul Graduate School of AI · Yale, Department of Psychiatry · University of Haifa, School of Public Health +3
Autonomous discovery of accelerator commissioning algorithms
Aug 7, 2026Thorsten HellertAutomated Algorithm Discovery Large Language Model-Guided Scientific Discovery
Lawrence Berkeley National Laboratory · Lawrence Berkeley National Laboratory, Berkeley, CA 94720, USA
OPERA: Operator-residual feedback for reliable autonomous optical experiments with language-model agents
Aug 6, 2026Ning Xu, Xiang Zheng, Fuqiang Zhong +4Feedback Control Autonomous Experimentation
Department of Computer Science and Technology, Tsinghua University, Beijing, China · ModelBest Inc., Beijing, China · School of Artificial Intelligence and Robotics, Hunan University, Changsha, China +1
Capability-Gated Planning: Cost-to-Goal Discovery and the Limits of Myopic Experiment Selection
Aug 5, 2026Ahmed Hassoon, Mark DredzeBelief-Space Planning Cost-Aware Inference
Johns Hopkins University
From Trajectories to Evidence: Auditable Experimental Records for Industrial Research Agents
Aug 5, 2026Zijie Zhuang, Changxin Lao, Pengbo Xu +13Data Provenance Evidence-Grounded Reasoning
Kuaishou Technology, Beijing, China
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
Aug 5, 2026Zhuohang Jiang, Yuxin Chen, Yongsen Pan +6Retrieval-Augmented Generation Recommender Systems
The Hong Kong Polytechnic University Hong Kong SAR, China · Kuaishou Technology Beijing, China · Southwest Jiaotong University Chengdu, SiChuan, China

Oct 8, 2026, cs.AIJ/K move · Enter open · S save

LLM-IDEA: Identifiability-Driven Experimental Agent for Autonomous Discovery of Mechanistic World Models

Surya Shetty, Ulisses Braga-Neto

Texas A&M University · Polara Labs Inc.

Autonomous Scientific Discovery Autonomous Experimentation Parameter Identifiability

Open paper AskPDF arXiv

Large language model agents are being increasingly deployed as autonomous scientists, designing experiments and inferring mechanistic world models with minimal human oversight. Yet identifiability is often overlooked: when a plateau is reached, the agent needs to know whether it is not yet capable enough or the model simply is not identifiable from the data, in which case no amount of further experimentation of the same kind can help. We propose the Identifiability-Driven Experimental Agent (LLM-IDEA) for closed-loop discovery with an identifiability engine that returns a three-way plateau verdict: capability limit, resolvable within the design class, or certified exhausted. On ODEBench, 60 of the 62 systems with free constants are identifiable at round 0; the RC circuit is certified exhausted for every experiment that protocol can run, and a harvesting model is resolvable by one added initial condition. The identifiability engine reproduces known verdicts on Lotka-Volterra, Van der Pol, Lorenz, and a pharmacokinetic model, where it recommends the intravenous arm pharmacologists use, and it ranks the depth scorer of our own benchmark last among four observation designs. On the DiscoverPhysics benchmark, it finds two public worlds whose explanation rubric rewards a distinction no legal experiment can make, and every model there with accurate trajectories failed the explanation grade (15 of 15, against 5 of 9 in identifiable worlds, p = 0.012). On the Alien Universe, a two-body testbed we propose in which a force law switches between a provably non-identifiable and an identifiable protocol, LLM-IDEA on the identifiable protocol reaches discovery depth at least three on 8/8 seeds versus 1/8 without it. An autonomous discovery agent can thus compute, rather than guess, whether a plateau calls for more search, a better experiment of the same kind, or a different kind of experiment.

Momentum

Related topics

Latest papers 95