Latest AI/ML News
2708 articles
arXiv:2608.13667v1 Announce Type: new Abstract: LLM agents in the ReAct paradigm alternate between reasoning, acting, and observing, but deliberate re…
arXiv:2608.13662v1 Announce Type: new Abstract: Coding agents have become the primary means of generating new code in many software projects, and the…
arXiv:2608.13630v1 Announce Type: new Abstract: We present ConceptFlow, a scikit-learn-compatible Python library for Formal Concept Analysis that cons…
arXiv:2608.13626v1 Announce Type: new Abstract: A hidden state signal can be decodable or causally usable without supporting a reusable action map. We…
arXiv:2608.13625v1 Announce Type: new Abstract: Signal temporal logic (STL) provides a formal language for specifying real-time properties of real-val…
arXiv:2608.13622v1 Announce Type: new Abstract: Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask f…
arXiv:2608.13621v1 Announce Type: new Abstract: A hidden Markov model (HMM) combines three roles: inference of a hidden-state belief from observations…
arXiv:2608.13618v1 Announce Type: new Abstract: A single clinical algorithm can deliver unequal accuracy across patient groups, and concern about such…
arXiv:2608.13617v1 Announce Type: new Abstract: Verifying whether clinical care follows evidence-based protocols is a natural neuro-symbolic problem,…
arXiv:2608.13612v1 Announce Type: new Abstract: Natural-language interfaces to enterprise data must translate underspecified requests into governed, e…
arXiv:2608.13608v1 Announce Type: new Abstract: Agentic "Continual Learning Harnesses", systems that pair an LLM with retrieval or memory to improve f…
arXiv:2608.13607v1 Announce Type: new Abstract: Frontier LLMs are updated frequently and typically outperform their predecessors in aggregate. But agg…
arXiv:2608.13606v1 Announce Type: new Abstract: The next generation of AI agents is increasingly moving beyond systems that answer isolated questions…
arXiv:2608.13605v1 Announce Type: new Abstract: Natural language provides robots with a flexible task interface, but target ambiguity in embodied envi…
arXiv:2608.13604v1 Announce Type: new Abstract: Detection of misunderstanding is an urgent problem to solve because communication has moved away from…
arXiv:2608.13598v1 Announce Type: new Abstract: Agent evaluation relies almost entirely on outcome metrics such as success rate, which capture whether…
arXiv:2608.13591v1 Announce Type: new Abstract: High-confidence errors in large language models are often treated as evidence of fragile internal infe…
arXiv:2608.13577v1 Announce Type: new Abstract: This position paper argues that the dominant paradigm of AI evaluation (which focuses on superhuman au…
arXiv:2608.13574v1 Announce Type: new Abstract: LLM agents increasingly operate as execution systems that invoke tools, modify local state, use persis…
arXiv:2608.13573v1 Announce Type: new Abstract: Large Language Model (LLM) serving has become a critical cloud workload, and realistic traces are esse…