The Tool Illusion: Rethinking Tool Use in Web Agents
arXiv:2604.03465v1 Announce Type: new Abstract: As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool …
Quality follows upgrading
All Articles
arXiv:2604.03465v1 Announce Type: new Abstract: As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool …
arXiv:2604.03527v1 Announce Type: new Abstract: Modern agentic workflows decompose complex tasks into specialized subtasks and route them to diverse models to minimize cost without sacrificing …
arXiv:2604.03512v1 Announce Type: new Abstract: Outage management in large-scale cloud operations remains heavily manual, requiring rapid triage, cross-team coordination, and experience-driven decisions under partial observability. …
arXiv:2604.03656v1 Announce Type: new Abstract: Generative Engine Optimization (GEO) is rapidly reshaping digital marketing paradigms in the era of Large Language Models (LLMs). However, current …
arXiv:2604.03240v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by grounding generation in external knowledge, yielding relevance responses that are aligned …
Iran said it will target U.S.-linked data centers with new missile strikes, as the war between the U.S. and Iran escalates.
arXiv:2604.03356v1 Announce Type: new Abstract: Artificial intelligence (AI) alignment is fundamentally a formation problem, not only a safety problem. As Large Language Models (LLMs) increasingly …
arXiv:2604.03904v1 Announce Type: new Abstract: Large language models (LLMs) frequently produce confident but incorrect answers, partly because common binary scoring conventions reward answering over honestly …
arXiv:2604.03853v1 Announce Type: new Abstract: Multivariate count models are often justified by their ability to capture latent dependence, but researchers receive little guidance on when …
arXiv:2604.03873v1 Announce Type: new Abstract: Black-box knowledge distillation for large language models presents a strict trade-off. Simple off-policy methods (e.g., sequence-level knowledge distillation) struggle to …
arXiv:2604.03387v1 Announce Type: new Abstract: Hume's account of causal judgment presupposes three representational conditions: experiential grounding (ideas must trace to impressions), structured retrieval (association must …
arXiv:2604.03506v1 Announce Type: new Abstract: Despite the large corpus of biology training text, the impact of reasoning models on biological research generally lags behind math …