arXiv
ArchAgent v2: A Case Study with the Data Prefetching Championship
Agentic artificial intelligence has shown great promise in automating algorithm design, but scaling similar technique...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
arXiv
Energy-Structured Latent World Models with Neural Time Fields for Physically Constistent Open-World Motion Planning
Physically consistent motion planning remains a fundamental challenge in embodied AI, as generated trajectories must ...
arXiv
SHE: Trajectory-driven Safety Harness Evolution for LLM Agents
The safety of large language model (LLM) agents depends not only on model weights but also on the agent harness that ...
arXiv
BDH-CQ: In-Context Learning with Recurrent Latent Reasoning
We introduce BDH-CQ, a reasoning model that combines in-context learning with recurrent latent reasoning. Inputs pres...
arXiv
Fusion Training for Mathematical Generalization in Large Language Models
Thinking Mode Fusion (TMF) enables large language models to support both concise responses and long-form reasoning by...
arXiv
DSLE: A Learning Environment for Dark Souls Boss Encounters
We introduce the Dark Souls Learning Environment (DSLE), a containerized platform that presents all 22 boss encounter...
arXiv
GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis
Foundation models are transforming business workflows and boosting productivity, yet they remain largely absent from ...
arXiv
From Values to Benchmarks: Evaluating Large Language Models for Governmental Use in Dutch
Large language models are increasingly being deployed in governmental settings, yet few existing evaluation framework...
arXiv
Multimodal Model Diffing for Feature Discovery and Control
Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause th...
arXiv
Beyond Naturalness: Probing Automated Text-To-Speech Evaluators on Linguistically Grounded Dimensions
Automated Text-to-Speech (TTS) evaluation methods (Mean Opinion Score (MOS) predictors and Audio Large Language Model...
HuggingFace
RoMeRL: Balancing Feedback Coverage and the Memory-Reward Trap in Self-Evolving Agent Memory via Reduced-Order Utility States
Learning-based memory systems for self-evolving LLM agents face two tightly coupled challenges. First, trajectory-ind...
HuggingFace
Sci-VBench: Evaluating Knowledge- and Reasoning-Intensive Video Generation in Science Domains
We introduce Sci-VBench, a comprehensive benchmark for evaluating knowledge- and reasoning-intensive video generation...