Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
Decentralized bandit systems often contain heterogeneous agents: rewards can change at individual agents even when the best action for the network stays the same. These local changes may cancel when r...
With the rapid development of Large language model (LLM), agent systems enhanced by LLMs show huge potential in being able to deal with complex tasks, especially involving multi-step thinking or inter...
3D single object tracking (SOT) in LiDAR point clouds is essential for autonomous systems, but remains challenging under sparse and incomplete observations. In such cases, different target points prov...
How and why does a recommender system fail the users it serves? Oftentimes, practitioners are left to improve their algorithms based on a combination of feedback from stakeholder teams, domain experti...
Zero-shot waypoint navigation requires vision-language models to select, from the current first-person observation, a sequence of spatial actions that is feasible for the agent and reaches the goal, p...
arXiv:2602.21061v2 Announce Type: replace Abstract: Many current paths to more advanced AI depend on the assumption that large language models (LLMs) can generalize learned relationships to solve com...
arXiv:2609.14045v1 Announce Type: new Abstract: Agentic learning systems are often required to adapt after deployment by observing new data and reusing prior knowledge under limited supervision or fe...
arXiv:2609.15915v1 Announce Type: new Abstract: Meta-reinforcement learning (meta-RL) enables agents to adapt to unseen tasks with limited experience. Despite its promise, the application of meta-RL...
arXiv:2607.10198v2 Announce Type: replace Abstract: Search APIs expose ranked snippets, URLs, and metadata on which agents decide whether to answer, search again, or fetch pages. We evaluate these in...
arXiv:2509.24975v4 Announce Type: replace-cross Abstract: Diffusion large language models (dLLMs) enable parallel generation and are promising for unit test generation (UTG), where efficient and larg...
arXiv:2603.19896v2 Announce Type: replace Abstract: Tool-using large language model (LLM) agents often face a fundamental tension between answer quality and execution cost. Fixed workflows are stable...
arXiv:2609.14819v1 Announce Type: cross Abstract: Large language models (LLMs) have a growing range of applications in medicine, and their evaluation is critical for ensuring they provide benefit and...
The paper introduces Vocalizer, a mobile app that lets users submit spoken online reviews enhanced by a large language model. A longitudinal study shows that users often use the AI to add detail and that interactive AI features boost confidence and willingness to share reviews. The authors also outline the benefits and challenges of embedding AI assistance in review-writing systems.
arXiv:2603.18740v3 Announce Type: replace-cross Abstract: Automated Code Review (ACR) systems integrating Large Language Models (LLMs) are increasingly adopted in software development workflows, rang...
The paper introduces SCoRE, an agentic framework for Visual Retrieval-Augmented Generation that explicitly selects and consolidates visual evidence before generating answers. It addresses two key challenges: sparse, scattered evidence and noisy exploration trajectories that obscure reasoning. By maintaining a textual ledger of relevant observations and reloading original images for a logical evidence sequence, SCoRE decouples reasoning from exploration and enforces strict visual grounding, with training that rewards evidence coverage, compactness, and answer correctness.
LongAgent is an agent-based method designed to extract predictive representations from heterogeneous longitudinal medical data. It autonomously searches over variable sets, temporal windows, and aggregation functions, using a history memory to guide exploration. On synthetic data, it achieves a mean prediction RMSE of 1.7376, outperforming the best non-agent baseline by 0.0151, and performs comparably to the best baseline on a real clinical dataset.
The article introduces personality engineering, a method that uses AI agents to precisely model negotiator personas based on established personality frameworks. It argues that AI agents, free from human limitations, can rigorously test canonical negotiation theory, which posits that success depends on balancing empathy and assertiveness. The authors propose using the interpersonal circumplex—specifically its warmth and dominance dimensions—as a foundational coordinate system for both theory testing and AI agent design.
OrchSLM is a routing framework that unifies non‑interactive orchestration methods for small language models (SLMs). It allows heterogeneous SLMs to independently generate candidate solutions while a router manages their cached outputs without further model interaction. By systematically probing OrchSLM, the study shows how orchestration behavior depends on task structure, model‑pool composition, and multi‑agent consensus.
The paper introduces Atria Dawn Preview, a foundation agentic language model aimed at scientific research and engineering workflows. Trained through a Verifiable Experience Pipeline, it performs competitively across 16 real‑world benchmarks, achieving the highest scores on five. The authors also present a detailed case study of human–AI collaboration, showing that while AI proposes methods and revisions, humans retain final decision‑making and guide the research direction.
The paper proposes AI Deployment Accountability Engineering (ADAE), a new subdiscipline focused on establishing measurable, continuous, and actionable accountability for AI systems once they are deployed. ADAE treats accountability as a deployment-layer property, aiming to ensure systems remain within acceptable risk limits, identify failure contexts, attribute failures across technical and human components, and translate technical failures into downstream consequences. The authors outline a research agenda built around four pillars—structured discovery of context-dependent failure modes, privacy-preserving accountability measurement, system-level risk analysis for agentic AI, and translation of technical failures into operational and institutional risks—to support timely intervention in safety-critical socio-technical environments.