Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2608. 15654v1 Announce Type: cross Abstract: Large language models can write fluent stories, but open-ended storytelling requires more than local fluency.
arXiv:2608. 16045v1 Announce Type: cross Abstract: LLM-based data-analysis tools are increasingly used to help users analyze messy spreadsheets and workbooks, from answering questions over uploaded files to generating code, summaries, and visualizations.
arXiv:2608. 16285v1 Announce Type: cross Abstract: Audio-Visual Segmentation (AVS) is a fundamental task in multimodal perception that performs pixel-level segmentation of sounding objects in videos by leveraging both visual and audio cues.
arXiv:2608. 16837v1 Announce Type: cross Abstract: Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation.
arXiv:2608. 16876v1 Announce Type: cross Abstract: We introduce Automatic Symbolic Regression (AutoSR), a fully automated system that instantiates Research-Space Symbolic Regression by searching persistent scientific investigations rather than isolated equations.
arXiv:2511. 17006v2 Announce Type: replace Abstract: Scaling test-time computation has been extended from language model reasoning to tool-augmented agents, where scaling involves not only thinking in tokens but also acting via tool calls that directly constrain environmental interaction.
arXiv:2510. 10813v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly applied to domains that require reasoning about other agents' behavior, such as negotiation, policy design, and market simulation.
arXiv:2602. 12276v2 Announce Type: replace Abstract: Test-time scaling has become a standard way to improve performance and boost reliability of neural network models.
arXiv:2603. 17216v2 Announce Type: replace Abstract: With the advent of AI agents, automated scientific discovery is becoming an increasingly plausible goal.
arXiv:2608. 15881v1 Announce Type: new Abstract: The Multiphysics Object-Oriented Simulation Environment (MOOSE) is an open-source finite-element framework for building multiphysics simulation applications.
arXiv:2608. 16710v1 Announce Type: new Abstract: As autonomous vehicles (AVs) approach Level 4 and Level 5 operational capability [SAE International, 2018], their on- board decision systems must handle not only safety-critical locomotion but also their subsequent moral weight.
Textual context such as news, reports, and logs can provide valuable signals for time series forecasting, especially when future dynamics are driven by external events that are not yet visible in hist...
Agent Skills can specify procedural and resource obligations for tool use, and language models instantiate them as concrete programs. However, when models turn this guidance into code for existing too...
Long-horizon robot manipulation chains many contact-rich skills into one multi-stage task. Vision-language-action (VLA) models increasingly master the individual skills, yet the chain still fails: err...
Humanoid robots hold great promise as general-purpose agents in human-centered environments, yet generalist vision-language-action (VLA) foundation models are not readily applicable to humanoid whole-body loco-manipulation. The high dimensionality and interdependence of humanoid motions make it challenging for conventional single-stage VLA architectures to coordinate locomotion, waist posture, and dual-arm manipulation effectively.
Language and vision-language models generate plausible embodied plans but do not guarantee executability, as their outputs can violate environment dynamics or act on incorrectly grounded entities. We present a neurosymbolic agent that factors long-horizon household tasks into task-directed visual exploration and constrained symbolic planning.
For years, web agents have worked one click at a time—and often fallen apart on long tasks. Microsoft Research’s Webwright makes a different bet: give the model a terminal and let it write the program instead.
Large Language Models (LLMs) have achieved remarkable progress in code generation, yet ensuring correctness in complex, repository-level tasks remains challenging. Existing approaches often use generated tests as static post-hoc validators, which limits their ability to guide implementation and may introduce misleading feedback when the tests themselves are incomplete or incorrect.
How autonomous agents broke two decades of capacity planning — and what to build instead The post Three Generations of Autoscaling — And Why Agentic Traffic Breaks All of Them appeared first on Towards Data Science .
This paper presents Chronocooked, a reinforcement learning (RL) benchmark suite for studying implicit interval timing in RL agents. Inspired by Overcooked, the suite comprises cooking scenarios that require temporal decision making.