arXiv:2608.06917v1 Announce Type: new Abstract: Recent Large Multimodal Models (LMMs) have achieved impressive performance in recipe generation from food…
Category: AI
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
arXiv:2608.06871v1 Announce Type: new Abstract: Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear,…
From Points to Edges: Edge-Conditioned Spectral Operators for Physics-Sensitive PDE Learning
arXiv:2608.06894v1 Announce Type: new Abstract: Neural operators have become a central tool for solving partial differential equations (PDEs), with…
SkillEval: Decomposing Agent Skill Quality into Interpretable Signals
arXiv:2608.06891v1 Announce Type: new Abstract: Agent skills provide reusable procedural knowledge that helps agents solve specialized tasks. As their use…
Evolving Parallel Algorithm Portfolios via Potential-Aware Instance Generation with LLMs
arXiv:2608.06808v1 Announce Type: new Abstract: The Automatic Construction of Portfolios via Large Language Models (LLM-ACP) suffers from poor…
Gated-BEPO: Confidence-Gated Bellman Credit Assignment for Large Language Model Agents
arXiv:2608.06861v1 Announce Type: new Abstract: Training large language model agents in long-horizon environments requires assigning credit from sparse…
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
arXiv:2608.06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution…
Mind the Gap: A Dual Knowledge Graph Framework for Unified Multi-task User Intent Inference
arXiv:2608.06752v1 Announce Type: new Abstract: This paper proposes DKG-MTI, a dual knowledge graph framework for unified multi-task user intent inference…
Surg-UniWorld: A Unified Surgical World Model with Multimodal Control Experts
arXiv:2608.06770v1 Announce Type: new Abstract: Controllable surgical world models can provide a generative foundation for surgical artificial…
LiFTER: A Grounded Neuro-Symbolic Microscope for Continuous-Time Dynamic Graph Forecasting
arXiv:2608.06765v1 Announce Type: new Abstract: Continuous-time dynamic graph models predict future links by compressing past interactions into neural…