Model releases, architecture work and prompting research on large language models — from frontier-lab announcements to the arXiv papers behind them.
arXiv:2605. 25160v2 Announce Type: replace Abstract: GUI agents powered by large language models are advancing rapidly, creating urgent needs for evaluation and training based on realistic environments.
arXiv:2606. 19868v1 Announce Type: new Abstract: Although large language models (LLMs) have shown strong capabilities across a wide range of tasks, their outputs often remain unreliable and may contain hallucinations, making uncertainty estimation (UE) essential for building trustworthy LLMs.
arXiv:2606. 19377v1 Announce Type: cross Abstract: Computational enzyme design requires generating proteins that scaffold catalytic residues and ligands, a task that demands both geometric accuracy and structural diversity from the underlying generative model.
arXiv:2602. 15707v2 Announce Type: replace-cross Abstract: Real-time conversational assistants for procedural manual tasks often depend on video input, which can be computationally expensive and compromise user privacy.
arXiv:2509. 23806v2 Announce Type: replace-cross Abstract: Concolic testing for neural networks alternates concrete execution with constraint solving to search for inputs that flip model decisions.
arXiv:2606. 19749v1 Announce Type: new Abstract: A new class of agentic review systems are emerging as a remedy to the pressure placed on peer review systems by AI-assisted research, but it is unclear how they should be evaluated.
arXiv:2602. 09689v2 Announce Type: replace Abstract: Fine-tuning large pre-trained models on a target distribution often improves in-distribution (ID) accuracy, but at the cost of out-of-distribution (OOD) robustness as representations specialize to the fine-tuning data.
arXiv:2606. 20537v1 Announce Type: new Abstract: Mainstream LLM serving systems reuse prefix work mainly through paged or radix key-value (KV) caches.
arXiv:2509. 19658v2 Announce Type: replace-cross Abstract: In-context imitation learning (ICIL) enables robots to learn tasks from prompts consisting of just a handful of demonstrations.
arXiv:2606. 19464v1 Announce Type: new Abstract: Autonomous agentic AI systems driven by Large Language Models (LLMs) introduce a new class of security, privacy, and compliance challenges: an agent that can invoke tools, manipulate data, install software, and coordinate with peer agents across organizational boundaries must be constrained not just by authentication and access control, but by the full structure of enterprise governance.
arXiv:2606. 19887v1 Announce Type: cross Abstract: Existing safety benchmarks target general adversarial scenarios but miss finance-specific risks.
arXiv:2606. 19560v1 Announce Type: new Abstract: Seasonal influenza infects millions of people and causes substantial morbidity and mortality in the United States each year, making accurate short-term forecasting a core public-health need.
arXiv:2606. 19651v1 Announce Type: new Abstract: Three-dimensional (3D) brain MRI is central to clinical neurology and neuro-oncology, where generative models could augment under-represented cohorts, simulate disease trajectories, and support privacy-preserving data sharing.
arXiv:2606. 19613v1 Announce Type: cross Abstract: We introduce StaminaBench, a benchmark that measures the stamina of coding agents: how many consecutive interaction turns (change requests) they can handle before failing.
arXiv:2606. 19819v1 Announce Type: cross Abstract: Decomposing compound sentences into atomic, verifiable claims is a prerequisite for reliable automated fact-checking.
arXiv:2606. 20014v1 Announce Type: cross Abstract: Reinforcement learning (RL) has achieved strong performance in sequential decision-making, yet scaling to complex multi-agent environments remains challenging due to sparse rewards, large state-action spaces, and the difficulty of learning coordinated strategies.
arXiv:2606. 19494v1 Announce Type: new Abstract: Multi-agent LLM deliberation, where agents exchange and revise answers over several rounds, is increasingly used to improve reasoning and accuracy, yet how and why it works is rarely modelled.
arXiv:2606. 19725v1 Announce Type: cross Abstract: Validating changes in low-level C firmware is expensive because unit tests (UTs) are fragile under strict build constraints, where missing headers, unresolved symbols, and dependency mismatches frequently prevent compilation and linking.
arXiv:2602. 14696v2 Announce Type: replace Abstract: Instruction fine-tuning of large language models (LLMs) often involves selecting a subset of instruction training data from a large candidate pool, using a small query set from the target task.
arXiv:2502. 19193v2 Announce Type: replace-cross Abstract: Social media platforms frequently impose restrictive policies to moderate user content, prompting the emergence of creative evasion language strategies.