From Intent to Execution: Composing Agentic Workflows with Agent Recommendation
arXiv:2605.03986v1 Announce Type: new Abstract: Multi-Agent Systems (MAS) built using AI agents fulfill a variety of user intents that may…
CreativityBench: Evaluating Agent Creative Reasoning via Affordance-Based Tool Repurposing
arXiv:2605.02910v2 Announce Type: new Abstract: Recent advances in large language models have led to strong performance on reasoning and environment-interaction…
SpecKV: Adaptive Speculative Decoding with Compression-Aware Gamma Selection
arXiv:2605.02888v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates large language model (LLM) inference by using a small draft model to…
Parametrizing Convex Sets Using Sublinear Neural Networks
arXiv:2605.03520v1 Announce Type: cross Abstract: We propose a neural parameterization of convex sets by learning sublinear (positively homogeneous and convex)…
Revisiting Graph-Tokenizing Large Language Models: A Systematic Evaluation of Graph Token Understanding
arXiv:2605.03514v1 Announce Type: cross Abstract: The remarkable success of large language models (LLMs) has motivated researchers to adapt them as…
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
arXiv:2605.02777v2 Announce Type: replace-cross Abstract: Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets…
Platonic representation of foundation machine learning interatomic potentials
Nature Machine Intelligence, Published online: 07 May 2026; doi:10.1038/s42256-026-01235-7 Li and Walsh show that a unified ‘platonic’ geometry emerges across…
Learning the chemical language of natural products
Nature Machine Intelligence, Published online: 07 May 2026; doi:10.1038/s42256-026-01241-9 A promising foundation model is developed for a range of downstream…
Reference-Sampled Boltzmann Projection for KL-Regularized RLVR: Target-Matched Weighted SFT, Finite One-Shot Gaps, and Policy Mirror Descent
arXiv:2605.02469v1 Announce Type: cross Abstract: Online reinforcement learning with verifiable rewards (RLVR) turns checkable outcomes into a scalable training signal,…
