Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2602.05843v3 Announce Type: replace Abstract: The advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. Howe...
arXiv:2605.17467v2 Announce Type: replace Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level rel...
arXiv:2605.24218v2 Announce Type: replace Abstract: Deep research agents extend the role of search engines from retrieving keyword-matched pages to synthesizing knowledge, fundamentally changing how...
arXiv:2607.03863v3 Announce Type: replace Abstract: Artificial intelligence has advanced scientific discovery, but most AI4Science systems remain fragmented tools that rely on humans to coordinate pr...
arXiv:2610.25458v2 Announce Type: replace Abstract: Small language models have improved to the point where a phone can plausibly screen its own calls, answering on an absent owner's behalf without se...
arXiv:2610.26433v2 Announce Type: replace Abstract: We study whether geometric relationships between conversation turns, memory texts, and queries can predict answer correctness before generation. We...
arXiv:2605.17558v2 Announce Type: replace-cross Abstract: Training tool-calling agents requires large-scale trajectory data with verifiable labels, yet existing approaches either synthesize environme...
arXiv:2606.00497v2 Announce Type: replace-cross Abstract: Deceptive web content, widely instantiated across the internet and commonly known as \textit{social-engineering attacks}, manipulates autonom...
arXiv:2606.13174v2 Announce Type: replace-cross Abstract: Interactive LLM agents increasingly work with users across tasks, yet remembering a previous correction does not ensure that the agent change...
arXiv:2610.05107v2 Announce Type: replace-cross Abstract: Search agents repeatedly make short decisions about relevance, evidence sufficiency, and search actions. Using generative language models for...
arXiv:2610.33158v1 Announce Type: new Abstract: Real-world environments undergo continual semi-static changes, requiring a memory representation that captures both the spatial and temporal evolution...
arXiv:2610.33396v1 Announce Type: new Abstract: Multi-object tracking in satellite video underpins persistent monitoring, yet offline-tuned trackers lack the onboard intelligence and efficiency to ad...
AgentOrch is a benchmark that compares global orchestration—where a complete workflow is generated upfront—with step‑by‑step interaction on 650 enterprise standard operating procedures and 3,220 runtime variants. Across all evaluated models, step‑by‑step remains more accurate, but the performance gap has narrowed by about 79% from early to recent models. The study identifies three methods—incremental workflow construction, revising workflows with execution feedback, and targeted training on complete workflows—that can further close the gap, improving global orchestration accuracy by up to 12.18 percentage points.
arXiv:2610.34564v1 Announce Type: new Abstract: Most action-conditioned video world models remain limited to a single player, while existing multiplayer models support only small, fixed groups of age...
arXiv:2610.34662v1 Announce Type: new Abstract: Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on...
arXiv:2610.34689v1 Announce Type: new Abstract: Knowledge distillation can transfer large multimodal models to compact models for autonomous driving, but uniform token-level matching can dilute plann...
arXiv:2610.34795v1 Announce Type: new Abstract: Cities must coordinate domains like infrastructure, mobility, environmental management, emergency response, and public services as conditions evolve. A...
arXiv:2610.35066v1 Announce Type: new Abstract: Vision-language navigation (VLN) requires an embodied agent to follow language instructions through 3D environments. Maintaining persistent episodic me...
arXiv:2610.35489v1 Announce Type: new Abstract: Deploying large vision-language models (LVLMs) on resource-constrained embodied agents for 3D visual question answering necessitates cloud-edge collabo...
arXiv:2610.35823v1 Announce Type: new Abstract: Browser agents do not just need more practice. They need to practice the right things. We introduce MiniWeb, a realistic miniature of the web comprisin...