Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2607. 08986v2 Announce Type: replace Abstract: We formalize a research result in the Lean 4 proof assistant by having a mathematician direct an AI system, and frame the activity as a formalization game.
arXiv:2607. 17947v1 Announce Type: new Abstract: Existing AI measurement frameworks quantify cognitive capability, task automation, or catastrophic risk, but none measure autonomous agency: the extent to which a system behaves in a self-directed way.
arXiv:2607. 16989v1 Announce Type: cross Abstract: Introduction.
arXiv:2607. 16345v1 Announce Type: cross Abstract: Modern agentic systems increasingly rely on skills: installable packages of natural language and code that teach an LLM agent to perform a domain task.
arXiv:2601. 07121v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used not only for problem solving but also for creative ideation; however, generating ideas that are both novel and coherent remains challenging.
arXiv:2605. 31581v2 Announce Type: replace Abstract: The same arguments often need to be evaluated under different external regimes.
arXiv:2607. 17100v1 Announce Type: cross Abstract: An AI research agent can improve the score it sees without finding a modelling change that works on new materials.
arXiv:2607. 16900v1 Announce Type: new Abstract: Training API-calling large language model (LLM) agents demands massive amounts of high-quality trajectories.
Large language models (LLMs) increasingly support science, but they can also convert hazardous scientific knowledge into actionable misuse guidance. Existing benchmarks often rely on templated queries disconnected from real-world hazards, and employ LLM-as-a-Judge paradigms without domain grounding.
LLM-based browser agents are rapidly changing the threat landscape for web security. Unlike traditional automation frameworks that execute predefined scripts, these agents can autonomously navigate websites, reason about page content, and interact with web interfaces using natural-language instructions.
Apply long-running coding agents to become a more productive engineer The post How to Run Claude Code Agents for 24+ Hours appeared first on Towards Data Science .
Predicting a football match before kickoff requires more than knowing past results: a model must use changing information and make a clear prediction before the answer is available. We present WorldCupArena, a dynamic benchmark for language models and deep-research agents.
Multimodal video misinformation detection is commonly formulated as a holistic video-understanding task, where the entire video and its associated content are processed and judged in a single pass. However, real-world misinformation often exhibits a sparse and compositional evidence structure: a reliable decision may depend on only a few coupled clues, while most video content contributes limited additional information.
Graphical User Interface (GUI) agents powered by vision-language models hold promise for automating real-world mobile tasks. However, progress is limited by the lack of high-coverage, long-horizon interaction trajectories collected from element-rich and rapidly evolving apps.
Organizations often pool dispersed information into one ranking and then allow many agents to act on that shared view. In a discovery problem, this can improve beliefs while reducing coverage.
Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\leq 4 \, \mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters.
Self-hosted AI agents read and write their own memory and configuration files to function. An agent may get compromised via corruption of its own state -- a compromise realized via legitimate OS system call invocation.
Large language models (LLMs) can assist GPU kernel generation, but their practical effectiveness depends on whether generated code can be reliably constrained, validated, profiled, and selected. This paper presents a harness-centered system for LLM-driven GPU kernel optimization in the MLSys 2026 FlashInfer AI Kernel Generation Contest on NVIDIA Blackwell B200 GPUs.
Most reinforcement learning controllers for these networks assume stationary conditions, and the few that handle change react to the external environment while leaving the network's internal state unexamined. We show that sustained non-stationarity damages this internal state directly: as objectives shift, neurons progressively fall dormant and the shared policy loses the capacity to learn.
LLM-based autonomous agents require external memory to overcome their statelessness and limited context window for long-term interaction and dynamic knowledge reasoning. However, existing memory retrieval methods often lack adaptability and sample efficiency, and struggle to retrieve the right mixture of memories from heterogeneous stores.