Latest papers from arXiv — updated daily across cs.AI, cs.LG, cs.CL, and cs.CV.
200 papers — updated daily from arXiv
Marco Zullich, Emily Schiller, Ivan Gentile +4 more
arXiv:2610.12493v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) tools have often been presented as methods to increase trust in machine learning models by making aspects of their algorithms…
Stuart Farmer
arXiv:2610.12536v1 Announce Type: new Abstract: EliteTable is a self-improving program-search algorithm guided by large language models (LLMs) that uses a fixed-capacity table of high-scoring solutions to guide new…
Yuyu Zhang
arXiv:2610.12542v1 Announce Type: new Abstract: Monte Carlo Tree Search (MCTS) is often proposed for scheduling directed-acyclic-graph (DAG) workflows, yet most studies never run the comparison that could refute it -…
Wei Yang, Qing Ping, Youzhi Luo +4 more
arXiv:2610.12593v1 Announce Type: new Abstract: The continued improvement of large language models increasingly depends on synthetic experience, yet effective data synthesis for interactive agents requires not only…
Scott C. Lowe, Sander W. Keemink
arXiv:2610.12596v1 Announce Type: new Abstract: Agentic large language models now tackle complex tasks, yet strategic reasoning over long horizons is under-studied: most agentic benchmarks are short and episodic, and…
Yiran Wu, Andrew Zhao, Yurui Chang +2 more
arXiv:2610.12598v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) provides reliable supervision for software engineering agents through executable tests, but binary rewards fail to…
Jiatan Huang, Zheyuan Zhang, Ziming Li +4 more
arXiv:2610.12655v1 Announce Type: new Abstract: LLM agents can execute increasingly complex tasks, but effective assistance also requires aligning their actions with goals and constraints that users may leave unstated. …
Ximing Lu, Aviral Kumar, Jan Kautz +2 more
arXiv:2610.12659v1 Announce Type: new Abstract: Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether the dataset…
Haotian Qiao, Robert P. Dick
arXiv:2610.12762v1 Announce Type: new Abstract: Hardware datasheets contain engineering specifications essential for component selection, system integration, and hardware compatibility verification. However, manual…
Julien Kordes, Reuben Dorent
arXiv:2610.12781v1 Announce Type: new Abstract: Aligning two independently pretrained unimodal encoders typically demands millions of paired examples. In this paper, we study the regime where only $N \sim 100$--$500$…
Janet Wang, Jiang Guo, Yi Xiang +6 more
arXiv:2610.12789v1 Announce Type: new Abstract: Self-evolving LLM agents typically improve how they act through accumulated experience, reflection, or skills. Yet even procedurally capable agents can fail when their…
Duy Nguyen, Lesly Miculicich, Bhavana Dalvi Mishra +5 more
arXiv:2610.12813v1 Announce Type: new Abstract: LLM agents increasingly operate over sensitive resources, such as private documents and mutable system states, which can create serious safety and security risks. Runtime …