Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2609.39909v1 Announce Type: cross Abstract: We introduce DoGBENCH (Documentation Generation Benchmark), to our knowledge, the first benchmark for generating and maintaining real user-facing sof...
arXiv:2609.40079v1 Announce Type: cross Abstract: While recent Multimodal Large Language Models (MLLMs) have shown promise in affective computing, their reasoning capabilities are largely confined to...
arXiv:2609.40195v1 Announce Type: cross Abstract: Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spann...
arXiv:2609.40284v1 Announce Type: cross Abstract: Computer use agents (CUAs), which use graphical user interfaces (GUIs) to complete tasks on a computer, have recently surpassed human performance on...
arXiv:2605.08693v3 Announce Type: replace Abstract: Skills provide an effective mechanism for improving LLM agents on complex tasks, yet in existing agent frameworks, their creation, refinement, and...
arXiv:2605.14211v4 Announce Type: replace Abstract: Long-horizon visuomotor tasks remain a fundamental challenge in AI, as current methods rely on hand-engineered rewards or action-labeled demonstrat...
arXiv:2609.27297v2 Announce Type: replace Abstract: Agentic science envisions many autonomous agents investigating concurrently while building on a shared, evolving body of scientific knowledge. This...
arXiv:2603.26741v2 Announce Type: replace-cross Abstract: Goal-conditioned visual navigation has been a long-standing testbed for embodied AI. We study a natural language-conditioned variant, languag...
arXiv:2609.38812v1 Announce Type: new Abstract: Terminal agents rely on self-verification to assess and correct their solutions as they solve tasks through interaction with command-line environments....
arXiv:2609.40103v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as automated judges for AI-generated content, yet a single judge is unreliable and even a panel...
arXiv:2609.38232v1 Announce Type: cross Abstract: Streaming spoken agents may take an external action before the available speech supports it, yet final-turn scores do not reveal whether each observe...
arXiv:2609.38413v1 Announce Type: new Abstract: Vision-language models (VLMs) can answer questions about hour-long videos, but processing every frame is prohibitively expensive, even though the evide...
arXiv:2609.39467v1 Announce Type: new Abstract: Pedestrian detection plays a crucial role in computer vision with applications in autonomous driving, surveillance, and public safety. However, real-wo...
arXiv:2409.14202v4 Announce Type: replace-cross Abstract: The instrumental variables (IVs) method is a leading empirical strategy for causal inference. Finding IVs is a heuristic and creative process...
arXiv:2607.22465v3 Announce Type: replace Abstract: Modern enterprise agent deployments consist of a heterogeneous pool of large language models (LLMs) having diverse capabilities and cost. Existing...
The paper introduces VHOP, a data generation framework and benchmark for visual agentic search, and VHOP-Router, an end‑to‑end training pipeline that turns a standard embedding model into an autoregressive multi‑step retriever operating directly in visual latent space. VHOP-Router eliminates the need for intermediate text queries, boosting retrieval accuracy from under 5% to 76.3% and improving task success rates by 52.7% while dramatically reducing token usage and API payloads. The approach generalizes to unseen difficulty levels and realistic test sets, offering an efficient solution that preserves native LLM capabilities.
arXiv:2609.38516v1 Announce Type: cross Abstract: Large language models (LLMs) can now improve themselves by revising the instructions they follow, and LLM agents are increasingly orchestrated to wor...
arXiv:2609.39304v1 Announce Type: cross Abstract: When an off-the-shelf coding agent is used directly as a robot policy, observing a browser-based 3D interface through screenshots and acting by posin...
The paper introduces the concept of stale binding, where large language models (LLMs) answer with outdated values despite having newer information in context. It presents Controlled In-Context Memory (CICM), a benchmark to track and test the use of updated information in conversations and agent logs. Experiments on open‑source models reveal an attention drift mechanism that favors old values, and the authors propose a simple attention‑redirecting intervention that largely corrects these errors without harming correct answers.
arXiv:2605.16679v3 Announce Type: replace-cross Abstract: End-to-end automation of realistic healthcare operations stresses three capabilities underrepresented in current benchmarks: policy density,...