arXiv AI

Discovery under Hypothesis Redundancy: A Geometric Theory of Discovery Bottlenecks

arXiv:2606. 14386v1 Announce Type: cross Abstract: Scientific discovery saturates when new hypotheses cease to provide independent information, even if the nominal hypothesis space remains large.

arXiv AI

Jul 21

Automated Discovery Has No Universally Superior Harness

arXiv:2607. 18235v1 Announce Type: cross Abstract: Autonomous discovery systems such as OpenEvolve and TTT-Discover are often used as general-purpose harnesses.

By Akshat Gupta, Jermaine Lei, Alexander Lu, Gopala Anumanchipalli, Leshem Choshen

llms agents

arXiv Machine Learning

Jul 7

Dictionaries, Not Darwin: Set-Level Selection Beats LLM Evolution in Scientific Equation Discovery

arXiv:2607. 04108v1 Announce Type: new Abstract: Large language models are increasingly used as evolutionary engines for scientific discovery: generate candidates, select winners, feed them back as parents, and repeat.

By Pan Li

llms

arXiv AI

Jun 30

Evidence-Informed LLM Beliefs for Continual Scientific Discovery

arXiv:2606. 29182v1 Announce Type: new Abstract: Open-ended scientific discovery with large language models (LLMs) increasingly operates as a long-horizon loop of hypothesis search and verification, where a reward signal guides which hypotheses to test next.

By Dhruv Agarwal, Reece Adamson, Andrew McCallum, Peter Clark, Ashish Sabharwal, Bodhisattwa Prasad Majumder

llms rag

arXiv AI

Jul 29

Structured Scaling of AI Discovery Across Diverse Scientific Domains

arXiv:2604. 19341v2 Announce Type: replace-cross Abstract: Scientific discovery often requires many cycles of proposing, testing, and refining candidate solutions.

By Haotian Ye, Haowei Lin, Jingyi Tang, Yizhen Luo, Rahul Thapa, Caiyin Yang, Chang Su, Rui Yang, Ruihua Liu, Rundao Li, Zeyu Li, Pengwei Sun, Chong Gao, Dachao Ding, Guangrong He, Miaolei Zhang, Lina Sun, Wenyang Wang, Yuchen Zhong, Zhuohao Shen, Puheng Li, Pan Lu, Bianxiao Cui, Di He, Jianzhu Ma, Junfeng Li, Hexi Baoyin, Yejin Choi, Stefano Ermon, Xiaowen Chu, Tongyang Li, Yuzhi Xu, James Zou

llms benchmarks

arXiv Machine Learning

Jul 30

Budget-Aware LLM Discovery via Cost-Calibrated Frontier Utility

arXiv:2607. 26828v1 Announce Type: new Abstract: Large language models increasingly support scientific and algorithmic discovery through inference-time search over evaluated candidates.

By Yansen Zhang, Yilu Liu, Tianyu Liu, Jiamin Chen, Xiaokun Zhang, Kai Xie, Xue Liu, Chen Ma, Yiyan Qi

llms benchmarks

arXiv Machine Learning

Jun 25

LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search

arXiv:2606. 25039v1 Announce Type: new Abstract: Recovering governing Ordinary Differential Equations (ODEs) from data is a central challenge in modeling dynamical systems across scientific domains.

By Nikhil Abhyankar, Sha Li, Sanchit Kabra, Naren Ramakrishnan, Yulia Gel, Chandan K. Reddy

llms benchmarks

arXiv AI

Aug 3

Library Reachability in LSR-Synth: How Anti-Memorization Design Changes the Measurement of Symbolic Discovery

arXiv:2607. 28684v1 Announce Type: new Abstract: Existing benchmarks for scientific equation discovery are largely composed of well-known equations available in the public domain, making it difficult to determine whether a model is discovering laws from data or merely recalling answers from its training corpus.

By Zhan'ao Yao, Liang Yin, Zhihao Gao, Boxuan Zhang, Xiaoyu Wu, Linjing Li, Rongyan Wang, Tingwei Chen, Youwei Wang, Xiaolin Zhao, Jiahui Shi, Jianjun Liu

llms benchmarks

arXiv AI

Jun 11

StatefulDiscovery: Evidence-Calibrated Claim Formation in Open-Ended Scientific Discovery

arXiv:2606. 11851v1 Announce Type: new Abstract: Open-ended scientific discovery asks agents to move beyond executing analyses for predefined questions.

By Jiayao Chen, Shi Liu, Linyi Yang

agents

arXiv Machine Learning

Jun 30

Evolution Fine-Tuning: Learning to Discover Across 371 Optimization Tasks

arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?

By Young-Jun Lee, Seungone Kim, Minki Kang, Alistair Cheong Liang Chuen, Zerui Chen, Seungho Han, Taehee Jung, Dongyeop Kang

llms agents reinforcement-learning fine-tuning benchmarks

arXiv AI

Jul 16

Representation-Based Exploration for Language Models: From Test-Time to Post-Training

arXiv:2510. 11686v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) promises to expand the capabilities of language models, but it is unclear if current RL techniques promote the discovery of novel behaviors, or simply sharpen those already present in the base model.

By Jens Tuyls, Dylan J. Foster, Akshay Krishnamurthy, Jordan T. Ash

llms reinforcement-learning

arXiv Machine Learning

Jun 26

Target-Aware Bandit Allocation for Scalable Surrogate Optimization in Chemical Space

arXiv:2606. 26657v1 Announce Type: new Abstract: Identifying high-utility candidates from massive discrete spaces under expensive evaluations is a recurring challenge across the sciences, with structure-based drug discovery as a prominent example.

By Mohammad Haddadnia, Yuvan Chali, Abhilash Jayaraj, Constance Kraay, Joana Reis, Felix Strieth-Kalthoff, Haribabu Arthanari

reinforcement-learning

arXiv AI

Jul 28

Action from Adjacent Set in Physical Space Outperforms the Best Prediction in World Models

arXiv:2607. 23602v1 Announce Type: cross Abstract: Controllers based on sampling and latent world models assign a predicted terminal cost to each candidate action sequence, choose the minimum, execute its first action block, and replan.

By Liangyu Li, Qingwen Liu, Mingqing Liu

Related stories