arXiv:2608. 05179v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly used across the scientific research lifecycle: ideation, literature search, experiment design and execution, analysis, manuscript drafting, and review.
By Tianyu Ding, Aditya Nannapaneni, Bingfan Liu, Ling Zhang
arXiv:2606. 05646v1 Announce Type: cross Abstract: Large language models (LLMs) have enabled powerful software engineering (SE) agents capable of navigating complex codebases and resolving real-world issues.
By Xuehang Guo, Zora Zhiruo Wang, Qingyun Wang, Graham Neubig, Xingyao Wang
TestJack is a scalable framework that audits large language model (LLM) coding agents by generating new tests for each trial, focusing on prompt requirements that may be violated. It keeps only the tests passed by the ground‑truth patch and re‑examines failures, providing replayable evidence for each confirmed error. In experiments across six model backends and five benchmarks, TestJack found that 34.4% of trials deemed correct actually violated task requirements, reducing the overall resolution rate from 50.6% to 33.2%.
By Shuangjie Yao, Hao Wang, Koushik Sen, Simin Chen, Baishakhi Ray, Dawn Song
arXiv:2604.16625v2 Announce Type: replace-cross
Abstract: Recent large language model (LLM) agents have shown promise in using execution feedback for test-time adaptation. However, robust self-improv...
By Weihua Du, Jingming Zhuo, Yixin Dong, Andre Wang He, Weiwei Sun, Zeyu Zheng, Manupa Karunaratne, Ivan Fox, Tim Dettmers, Tianqi Chen, Yiming Yang, Sean Welleck
AgentFold is a multi‑agent framework that treats protein‑folding model design as a closed‑loop search over executable code variants. Starting from the ESMFold codebase, the agents generate hypotheses, modify and debug code, evaluate model variants, and store both successes and failures in structured memory, guided by an MCTS‑style policy that allocates GPU resources. In an engineering‑scale experiment, AgentFold explored about 80 variants using 5,000 GPU‑hours and 170 million LLM tokens, improving the best lDDT score by 7.5% over independent Codex proposals and outperforming a random‑search baseline, while also uncovering empirical design patterns such as the benefits of early, soft, learnable priors.
By Mingquan Liu, Jiangyu Chen, Hanqun Cao, Xujun Zhang, Pengsen Ma, Xiangru Tang, Shuting Jin, Zhuo Yang, Tianfan Fu, Fang Wu, Xiangxiang Zeng
SAGE-Loop is a new closed‑loop, self‑adaptive AutoML framework that uses large language models to generate and validate machine learning pipelines in multiple rounds, allowing trial‑and‑repair and adaptive ensemble selection for both supervised and unsupervised tasks. It addresses the lack of instant feedback and correction in existing AutoML by enabling process‑level recovery from failures and dynamic use of model diversity. Experiments on 20 public datasets show consistent improvements in performance and stability across classification, regression, and clustering, and demonstrate the system’s ability to recover from execution failures.
By Junquan Gu, Shibo Cui, Xiangfeng Luo, Hang Yu