Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2607. 28691v1 Announce Type: cross Abstract: Personalized AI agents are often configurable without giving users control over the artifacts that determine their future behavior.
arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.
arXiv:2607. 29496v1 Announce Type: new Abstract: We study transcript management for fixed, finite-precision causal Transformers.
arXiv:2607. 28829v1 Announce Type: cross Abstract: Self-improving federated agent networks keep training after deployment by collecting new trajectories with the current policy and feeding them back into later rounds.
arXiv:2607. 23332v2 Announce Type: replace Abstract: Creating a reusable tool is an investment: an agent pays a fixed cost now in exchange for the potential of future reuse.
arXiv:2602. 07339v2 Announce Type: replace Abstract: Diffusion-based trajectory planners can model multi-modal driving behavior, but their iterative denoising process introduces a latency bottleneck for real-time closed-loop deployment.
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv:2607. 28977v1 Announce Type: cross Abstract: Machine learning of Hamiltonian dynamics has driven growing interest in Hamiltonian neural networks (HNNs), which encode Hamilton's equations of motion into the learning architecture.
arXiv:2604. 04468v2 Announce Type: replace Abstract: Evaluating retail strategies before deployment is difficult, as outcomes are determined across multiple stages, from seller-side persuasion through buyer-seller interaction to purchase decisions.
arXiv:2607. 29559v1 Announce Type: new Abstract: Reinforcement Learning (RL) systems are typically trained using a single, well-specified scalar reward function.
arXiv:2607. 29078v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias.
arXiv:2607. 21106v2 Announce Type: replace Abstract: Effective memory is crucial for LLM agents, yet constructing it effectively remains challenging.
arXiv:2607. 29516v1 Announce Type: cross Abstract: AI coding agents are generating code at volumes that exceed the capacity of traditional peer review.
arXiv:2603. 20075v2 Announce Type: replace-cross Abstract: Compilers are critical to modern computing, yet fixing compiler bugs is difficult.
arXiv:2607. 28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial variation in the demands of individual samples.
arXiv:2602. 10429v2 Announce Type: replace-cross Abstract: AIvilization v0 is a publicly deployed large-scale artificial society that couples a resource-constrained sandbox with a unified LLM-agent architecture, aiming to sustain long-horizon autonomy while remaining executable under a rapidly changing environment.
arXiv:2607. 29031v1 Announce Type: cross Abstract: Existing autonomous-driving world models typically perform dense prediction of future videos, occupancy states, BEV representations, or agent motion.
arXiv:2601. 02430v3 Announce Type: replace-cross Abstract: Web applications (web apps) have become a key arena for large language models (LLMs) to demonstrate their code generation capabilities and commercial potential.
arXiv:2607. 28916v1 Announce Type: cross Abstract: Multistep credit assignment is critical for sample-efficient reinforcement learning, yet managing off-policy bias in Q-learning remains a fundamental challenge.
arXiv:2607. 27690v2 Announce Type: replace-cross Abstract: We introduce LabEvolver, a training-free framework that equips safe and grounded wet-lab agents with episodic memory from execution experience.