Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2602. 16965v2 Announce Type: replace Abstract: We study the decentralized multi-player stochastic bandit problem over a continuous, Lipschitz-structured action space where hard collisions yield zero reward.
arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.
arXiv:2606. 05559v1 Announce Type: new Abstract: Deployed large language model agents must adapt to distribution shift in dynamic environments.
arXiv:2606. 05793v1 Announce Type: cross Abstract: While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging.
arXiv:2606. 06416v1 Announce Type: cross Abstract: Inference-time skill augmentation provides a lightweight way to improve data-analytic agents by injecting reusable procedural knowledge without updating model parameters.
arXiv:2605. 16138v2 Announce Type: replace Abstract: Neural architecture search (NAS) is a powerful approach for automating model design, but existing methods often optimize for accuracy alone or rely on proxy metrics such as bit operations (BOPs) that correlate poorly with hardware cost.
arXiv:2606. 05597v1 Announce Type: new Abstract: Training vision-language web agents with multi-step RL is compute-intensive, with two dominant forms of inefficiency: idle GPUs in synchronous RL, and trajectories that use more steps and tokens than necessary.
arXiv:2606. 05404v1 Announce Type: cross Abstract: Time series are often embedded in rich contexts that are essential for holistic modeling.
arXiv:2605. 31278v2 Announce Type: replace-cross Abstract: Reliable evaluation of agentic systems requires unbiased estimates with valid uncertainty, but standard practice navigates between costly human annotation and biased LLM-as-judge proxies.
arXiv:2606. 06344v1 Announce Type: new Abstract: Probabilistic inference over spatially embedded variables requires beliefs that respect $SE(3)$ symmetry, yet existing equivariant networks produce only scalars and vectors -- not the rank-2 precision tensors needed for anisotropic uncertainty, and single-component messages collapse multi-modal energy landscapes to physically meaningless averages.
arXiv:2602. 19373v3 Announce Type: replace Abstract: Deep reinforcement learning systems often suffer from unstable training dynamics due to non-stationarity, where learning objectives and data distributions evolve over time.
arXiv:2606. 06011v1 Announce Type: cross Abstract: In this work, we propose a framework that combines multi-agent reinforcement learning (MARL) with model-based control to achieve safe, dynamically feasible actions in cooperative multi-agent tasks.
arXiv:2606. 05922v1 Announce Type: cross Abstract: AI agents rely on a harness of skills, tools, and workflows to solve complex problems.
arXiv:2603. 03955v2 Announce Type: replace Abstract: Post-training with reinforcement learning (RL) has recently shown strong promise for advancing multimodal agents beyond supervised imitation.
arXiv:2602. 21889v2 Announce Type: replace-cross Abstract: Predictions from ML models support human decision making in several fields, including high-stakes ones such as healthcare and the judiciary.
arXiv:2606. 06391v1 Announce Type: cross Abstract: Sharing the financial impact of rare adverse events across a group can soften extreme individual burdens, but any participant made worse off by the arrangement has reason to leave.
arXiv:2606. 06493v1 Announce Type: cross Abstract: For a humanoid robot to be deployed in the real world, the choice of command space (i.
Modelling individual decision-making during infectious disease outbreaks is crucial for understanding behavioural dynamics and informing effective public health interventions. Prior work has shown that large language models can simulate realistic human behaviour by generating agent decisions based on demographic prompts and situational context.
Mortality forecasting plays an important role in actuarial and policy decision-making, but its implementation remains technically complex and inaccessible to non-expert users. This project proposes a reliable large language model (LLM)-integrated interface that improves usability while maintaining statistical power.
Language-model agents act through repeated cycles of observation, reasoning, and action selection, making safety monitoring depend on both internal model state and environment context. We study reward-hacking monitors in ReAct-style agents acting in Gameable ALFWorld and WebShop.