Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 09939v1 Announce Type: cross Abstract: Production teams deploying LLM chat agents face a specific quality assurance gap: existing evaluation tools test individual responses or simulate social interactions, but none systematically verify whether real users can achieve their goals through multi-turn conversation.
arXiv:2608. 10016v1 Announce Type: cross Abstract: Heterogeneous federated systems require agents to learn and exchange informative representations despite differences in data distributions, sensing modalities, model architectures, latent dimensionalities, and local learning objectives.
arXiv:2608. 10660v1 Announce Type: cross Abstract: Continuous and reliable localization is essential for autonomous driving.
arXiv:2608. 10976v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models can connect scene understanding, semantic reasoning, and trajectory generation for autonomous driving.
arXiv:2608. 10875v1 Announce Type: cross Abstract: Large language model (LLM) agents are increasingly deployed as personal assistants.
arXiv:2605. 20173v2 Announce Type: replace Abstract: Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural object.
arXiv:2608. 10330v1 Announce Type: new Abstract: AI agents are increasingly being developed to assist humans in various applications, and Large Language Models and other deep network architectures are considered to be state of the art for such agents.
arXiv:2602. 13319v2 Announce Type: replace Abstract: Perspective-aware AI requires modeling evolving internal states---goals, emotions, contexts---not merely preferences.
Mobile GUI agents remain brittle when deployed to applications absent from source training. We study novel-app generalization under a limited target interaction budget and without target demonstrations.
Uncertainty quantification (UQ) methods for language models are typically evaluated on single-turn outputs, where uncertainty is attached to one generated answer. For LLM agents, however, the unit of observation is an interactive trajectory, where the model can ask clarifying questions, call tools, update state, and make intermediate decisions whose errors propagate to the final outcome.
Enterprise practitioners read agent leaderboards as if they ranked agent capability. We show, across three open agent-trace benchmarks (TheAgentCompany, $τ^2$-bench, and AppWorld), that the agent main effect accounts for less than 3% of total variance in every dataset and check type, while the agent-by-task interaction accounts for 7-23%.
AI agents are increasingly used in mathematics research, but it is often unclear how to use them effectively. Towards this, we present an extensive case study of how AI was used to improve bounds on the Grothendieck constant $K_G$, which captures the hardness between combinatorial problems and their continuous relaxations.
Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple domains and feedback paradigms. Prefix-aware routing improves inference efficiency through cache reuse and load balancing, but it does not control how heterogeneous rollout sessions compete for KV-cache capacity.
When a tool-using agent is given the same task in a different language, does it still take the same steps? Multilingual evaluation rarely asks: it compares final answers and discards the actions.
Agentic coding READMEs like CLAUDE. md grow without bound in real repositories, stopping only when the repository retires or someone rewrites the file wholesale.
Long-horizon egocentric video is a rich substrate for wearable AI assistants, but object-centric questions such as where an item was moved, when it last changed state, or why it was relocated remain difficult because caption- and transcript-based memories rarely preserve persistent object identity or structured spatial change. Existing long-video QA methods mainly emphasize temporal grounding and clip retrieval, while prior 3D scene-graph methods typically assume stronger geometry than free-motion wearable RGB video provides, including point clouds, RGB-D input, posed views, sparse reconstruction, or reconstructed scenes.
Large language model (LLM) agents are increasingly deployed as personal assistants. Existing evaluations, however, mostly use short, self-contained requests in static environments.
I replayed the same 27 real production tasks through two local models, one hardware upgrade apart, to find out what it actually takes to replace Claude as the brain behind a 90-tool personal agent. The post Can a Local LLM Run My AI Assistant?
Understanding both expressed and evoked emotions is critical for multimodal large language models (MLLMs) to achieve comprehensive affect-aware interactions. However, existing benchmarks typically examine expressed and evoked emotions in isolation or are constrained to coarse-grained and incomplete affective characterizations.
Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress. Raw interaction traces preserve such information but are long and noisy to condition on, whereas text-only skills often omit the visual state that makes a procedure applicable.