Untitled Story

arXiv:2603.29953v1 Announce Type: new Abstract: How reliably can structured intent representations preserve user goals across different AI models, languages, and prompting

arXiv:2604.00025v1 Announce Type: cross Abstract: Standard evaluation protocols reveal a counterintuitive phenomenon: on 7.7% of benchmark problems spanning five datasets, larger

arXiv:2604.05013v1 Announce Type: cross Abstract: Current LLM coding agents are predominantly trained on composite benchmarks (e.g., bug fixing), which often leads to

arXiv:2604.27891v1 Announce Type: new Abstract: Agent orchestration frameworks -- LangGraph, CrewAI, Google ADK, OpenAI Agents SDK, and others -- place an external orchestrator

arXiv:2604.18789v1 Announce Type: new Abstract: Reinforcement Learning from Human Feedback (RLHF) is central to aligning Large Language Models (LLMs), yet it introduces a critical

arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers.

arXiv:2605.08496v1 Announce Type: new Abstract: Current adversarial robustness methods for large language models require extensive datasets of harmful prompts (thousands to

arXiv:2603.19715v1 Announce Type: new Abstract: Formal verification via interactive theorem proving is increasingly used to ensure the correctness of critical systems, yet