arXiv:2603.24239v1 Announce Type: cross
Abstract: Dynamism is common in AI computation, e.g., the dynamic tensor shapes and the dynamic control flows in models. Due to the long compilation time, existing runtime compilation damages the model efficienc…
arXiv:2603.23688v1 Announce Type: cross
Abstract: Background: Determining an adequate sample size is essential for developing reliable and generalisable clinical prediction models, yet practical guidance on selecting appropriate methods remains limite…
arXiv:2603.24472v1 Announce Type: cross
Abstract: Self-distillation has emerged as an effective post-training paradigm for LLMs, often improving performance while shortening reasoning traces. However, in mathematical reasoning, we find that it can red…
arXiv:2603.23961v1 Announce Type: new
Abstract: Deep-sea cold seep stage assessment has traditionally relied on costly, high-risk manned submersible operations and visual surveys of macrofauna. Although microbial communities provide a promising and mo…
arXiv:2603.23583v1 Announce Type: cross
Abstract: The accurate prediction of protein-RNA binding affinity remains an unsolved problem in structural biology, limiting opportunities in understanding gene regulation and designing RNA-targeting therapeuti…
arXiv:2603.24580v1 Announce Type: cross
Abstract: Retrieval-augmented generation (RAG) systems are increasingly used to analyze complex policy documents, but achieving sufficient reliability for expert usage remains challenging in domains characterize…
arXiv:2603.08566v2 Announce Type: replace-cross
Abstract: DARPA’s AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and op…
arXiv:2510.15259v3 Announce Type: replace
Abstract: Most commodity software lacks accessible Application Programming Interfaces (APIs), requiring autonomous agents to interact solely through pixel-based Graphical User Interfaces (GUIs). In this API-fr…
arXiv:2602.24055v4 Announce Type: replace
Abstract: This paper proposes CIRCLE, a six-stage, lifecycle-based framework to bridge the reality gap between model-centric performance metrics and AI’s materialized outcomes in deployment. Current approaches…
arXiv:2601.10402v5 Announce Type: replace
Abstract: The advancement of artificial intelligence toward agentic science is currently bottlenecked by the challenge of ultra-long-horizon autonomy, the ability to sustain strategic coherence and iterative c…