Quality follows upgrading
Academic
arXiv:2603.16210v1 Announce Type: new Abstract: Safety alignment in large language models (LLMs) is commonly implemented as a single static policy embedded in model parameters. However, …
arXiv:2603.15831v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents in uncertain, sequential decision-making contexts. Yet it remains poorly understood …
arXiv:2603.15952v1 Announce Type: new Abstract: Large language models (LLMs) are capable of emulating reasoning and using tools, creating opportunities for autonomous agents that execute complex …
arXiv:2603.15885v1 Announce Type: new Abstract: Critical infrastructure increasingly incorporates embodied AI for monitoring, predictive maintenance, and decision support. However, AI systems designed to handle statistically …
arXiv:2603.15978v1 Announce Type: new Abstract: Customer service automation is undergoing a structural transformation. The dominant paradigm is shifting from scripted chatbots and single-agent responders toward …
arXiv:2603.15653v1 Announce Type: new Abstract: Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, …
arXiv:2603.16161v1 Announce Type: new Abstract: Agentic Reinforcement Learning (RL) shows promise for complex tasks, but Text-to-SQL remains mostly restricted to single-turn paradigms. A primary bottleneck …
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:2603.16207v1 Announce Type: new Abstract: As Large Language Models (LLMs) transition from information providers to embodied agents in the Internet of Things (IoT), they face …
arXiv:2603.15666v1 Announce Type: new Abstract: Existing memory systems for language agents address memory management: how to retrieve and page more information within a context budget. …
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:2603.15670v1 Announce Type: new Abstract: Real-world decision-making, from tax compliance assessment to medical diagnosis, requires aggregating multiple noisy and potentially contradictory evidence sources. Existing approaches …