…AI agents move from chat interfaces to systems that read private data, call tools, and execute multi-step workflows, guardrails become a last line of defense against concrete deployment harms. In these…
…With iterative human-in-the-loop harness refinement, GPP became the first AI system to complete Pokemon Blue, Yellow Legacy on hard mode, and Crystal without a lost battle. In the hardest…
…reliability through comprehensive system design encompassing prompt compilation, policy validation, and execution safeguards rather than relying solely on base model performance. AI-generated summary We study reliability in autonomous language-model agents…
…agents learn to generate kernels that score well in sandboxes but introduce interface incompatibilities, compilation-stack conflicts, and silent correctness degradation when integrated into real systems. We introduce FastKernels , a kernel benchmark…
…ForeSci turns forward-looking AI research judgement into a controlled benchmark for evaluating research agents as decision-making systems . View arXiv page View PDF Add to collection Community AI research often requires…
…AI-generated summary Agentic large language model systems have demonstrated strong capabilities. However, their reliance on language as the universal interface fundamentally limits their applicability to many real-world problems, especially in…
…difficult to draw conclusions about how these systems perform for patients reporting symptoms in everyday life. We deployed SymptomAI, a set of conversational AI agents for end-to-end patient interviewing and…
…A Process-Centric Benchmark of Autonomous GUI Agents in Professional Cross-Application Environments (2026) FileGram: Grounding Agent Personalization in File-System Behavioral Traces (2026) AlphaEval: Evaluating Agents in Production (2026) Beyond Binary…
…Such informative lab notes preserve evolving scientific reasoning and author uncertainty , rather than polished final results exhibited in publications, providing a valuable opportunity for AI to engage in scientific exploration at a…
…AI-generated summary Autonomous scientific research is significantly advanced thanks to the development of AI agents . One key step in this process is finding the right scientific literature, whether to explore existing…