Quality follows upgrading
All Articles
arXiv:2603.15973v1 Announce Type: new Abstract: This paper contains the first formal proof that safety is non-compositional in the presence of conjunctive capability dependencies: two agents …
arXiv:2603.15641v1 Announce Type: new Abstract: Recursive reasoning models such as Hierarchical Reasoning Model (HRM) and Tiny Recursive Model (TRM) show that small, weight-shared networks can …
arXiv:2603.15888v1 Announce Type: new Abstract: With AsgardBench we aim to evaluate visually grounded, high-level action sequence generation and interactive planning, focusing specifically on plan adaptation …
arXiv:2603.15903v1 Announce Type: new Abstract: Natural languages have been argued to evolve under pressure to efficiently compress meanings into words by optimizing the Information Bottleneck …
arXiv:2603.15773v1 Announce Type: new Abstract: This work investigates how effectively large language models (LLMs) and their tokenization schemes represent and generate Arabic root-pattern morphology, probing …
arXiv:2603.15976v1 Announce Type: new Abstract: While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional …
arXiv:2603.16110v1 Announce Type: new Abstract: Enterprise IT support is constrained by heterogeneous devices, evolving policies, and long-tail failure modes that are difficult to resolve centrally. …
arXiv:2603.15668v1 Announce Type: new Abstract: As agentic artificial intelligence systems scale across globally distributed and long lived infrastructures, secure and policy compliant communication becomes a …
arXiv:2603.15969v1 Announce Type: new Abstract: The Romansh language has several regional varieties, called idioms, which sometimes have limited mutual intelligibility. Despite this linguistic diversity, there …
arXiv:2603.15639v1 Announce Type: new Abstract: AI agents are increasingly granted economic agency (executing trades, managing budgets, negotiating contracts, and spawning sub-agents), yet current frameworks gate …
arXiv:2603.16045v1 Announce Type: new Abstract: Small language models (sLLMs) are increasingly deployed on-device, where imperfect user prompts--typos, unclear intent, or missing context--can trigger factual errors …
arXiv:2603.16060v1 Announce Type: new Abstract: The dominant paradigm for improving mathematical reasoning in language models relies on Reinforcement Learning with verifiable rewards. Yet existing methods …