Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2604.08304v5 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) improves large language models (LLMs) with external knowledge, but this access path creates security ris...
arXiv:2604.18235v3 Announce Type: replace-cross Abstract: Search agents achieve strong question-answering performance through multi-turn interactions with search engines, with Group Relative Policy O...
arXiv:2605.13119v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models are effective robot action executors, but they remain limited on long-horizon tasks due to the dual burde...
arXiv:2605.17862v2 Announce Type: replace-cross Abstract: Scaling on-policy distillation (OPD) for large language models (LLMs) confronts a fundamental tension: asynchronous execution is necessary fo...
arXiv:2607.18360v2 Announce Type: replace-cross Abstract: GPTZero found 53 NeurIPS 2025 accepted papers with hallucinated citations, and venues now screen submissions with automated reference checker...
arXiv:2610.18880v1 Announce Type: new Abstract: High-throughput perturbation screens increasingly use machine-learning models to predict the effects of gene combinations that were never measured. A d...
arXiv:2610.19046v1 Announce Type: new Abstract: Information-theoretic exploration is of primary interest in methodological studies of reinforcement learning (RL) and computational cognitive neuroscie...
arXiv:2610.19103v1 Announce Type: new Abstract: Group-based reinforcement learning enables large language model agents to learn from sparse outcome rewards in long-horizon tasks. Recent methods deriv...
arXiv:2610.19298v1 Announce Type: new Abstract: Reinforcement learning for code usually rewards passing tests, which a model can do while remaining wrong on the inputs the tests do not cover. A progr...
arXiv:2610.19349v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) provides no reward-relative learning signal when all rollouts receive identical rewards. In long-horizon task...
arXiv:2610.19429v1 Announce Type: new Abstract: This paper presents a comprehensive comparison of four representative reinforcement learning (RL) methods in autonomous vehicle (AV) decision-making, i...
arXiv:2610.19439v1 Announce Type: new Abstract: While LLM-based agent systems have demonstrated remarkable proficiency in reasoning and solving complex real-world tasks, they also come with substanti...
arXiv:2610.20514v1 Announce Type: new Abstract: Evaluations of classifiers (AI or human or agents) often assume a batch setting in which every agent produces labels on every example in a test set, wh...
arXiv:2610.20256v1 Announce Type: new Abstract: Long-horizon agents must coordinate reasoning, tool use, and environment feedback over extended interactions. Learning from sparse outcome rewards requ...
arXiv:2610.20261v1 Announce Type: new Abstract: Deploying a general-purpose model as an agent means running it inside a product-specific runtime harness that decides which actions are executable, how...
arXiv:2610.20486v1 Announce Type: new Abstract: In reinforcement learning, an agent must explore an unknown environment to learn how to make good decisions. Unlike methods that can freely sample any...
arXiv:2610.20576v1 Announce Type: new Abstract: Post-training binds the competence of an LLM agent to the interface it was trained on. Semantics-preserving perturbations of that interface, such as re...
arXiv:2610.18881v1 Announce Type: cross Abstract: Voice agents built on large language models (LLMs) now handle customer calls, but in regulated applications completing the task is not enough: the ag...
arXiv:2610.18933v1 Announce Type: cross Abstract: Modern coding agents are fundamentally reshaping the role of human input for computational research: they write code, launch in silico experiments, a...
arXiv:2610.19159v1 Announce Type: cross Abstract: Can AI agents carry out research on open scientific problems? We introduce Into the Unknown, a benchmark that provides an agent with a science paper...