The PyTorch Foundation said Alibaba Cloud and Cambricon have joined as Platinum members and Ant Group has joined as a Gold member, a grouping the…
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
arXiv:2606.01139v4 Announce Type: replace Abstract: Agent skills are procedural artifacts that enable LLM agents to execute workflows, verify constraints,…
MemMA: Coordinating the Memory Cycle through Multi-Agent Reasoning and In-Situ Self-Evolution
arXiv:2603.18718v2 Announce Type: replace Abstract: Memory-augmented LLM agents maintain external memory banks to support long-horizon interaction, yet…
MemCoRe: Recovering Evidence from Progressively Compressed Factual Knowledge for Agent Memory
arXiv:2602.07885v3 Announce Type: replace Abstract: Memory systems enable LLM agents to consolidate and retrieve relevant evidence from the factual…
RL-VLA$^3$: A Flexible and Asynchronous Reinforcement Learning Framework for VLA Training
arXiv:2602.05765v3 Announce Type: replace Abstract: Reinforcement learning (RL) has emerged as a critical paradigm for post-training…
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design
arXiv:2602.13769v4 Announce Type: replace Abstract: Automating heuristic design in complex, experiment-driven domains requires more than iterative…
The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
arXiv:2603.08234v2 Announce Type: replace Abstract: With the rapid advancement of large language models (LLMs), the safety of LLMs has become a critical…
AI News Brief Hourly Summary 2026-09-08 03h : 11 posts
11 posts published in the last hour 00:32A Survey on Semantic Modeling for Building Energy Management 00:32Quality-diversity in dissimilarity spaces 00:32Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning 00:32Active Inference for an Intelligent Agent in Autonomous…
A Survey on Semantic Modeling for Building Energy Management
arXiv:2404.11716v4 Announce Type: replace Abstract: Building Energy Management (BEM) is central to reducing energy use and CO2 emissions in the building…
Quality-diversity in dissimilarity spaces
arXiv:2211.12337v4 Announce Type: replace Abstract: The theory of magnitude provides a mathematical framework for quantifying and maximizing diversity. We…
Achieving Olympiad-Level Geometry Large Language Model Agent via Complexity Boosting Reinforcement Learning
arXiv:2512.10534v5 Announce Type: replace Abstract: Large language model (LLM) agents exhibit strong mathematical problem-solving abilities and can even…
Active Inference for an Intelligent Agent in Autonomous Reconnaissance Missions
arXiv:2510.17450v2 Announce Type: replace Abstract: We develop an active inference route-planning method for the autonomous control of intelligent agents.…
Procedural Content Generation via Generative Artificial Intelligence
arXiv:2407.09013v3 Announce Type: replace Abstract: The attempt to utilize machine learning in procedural content generation (PCG) has been made in the…
What Matters, When? Diagnosing and Improving Conditional Visual Grounding in Visuomotor Imitation Policies
arXiv:2609.05376v1 Announce Type: cross Abstract: Visuomotor imitation policies can achieve high performance under in-distribution visual conditions yet…
When LLM Decompilers Recompile More and Preserve Less
arXiv:2609.05370v1 Announce Type: cross Abstract: Decompilation recovers high-level source from compiled machine code and serves as a foundation for…
RegionFed: Federated Learning for Personalized Query Understanding in Heterogeneous Retail Environments
arXiv:2609.05403v1 Announce Type: cross Abstract: Retail search systems serve diverse geographic regions with distinct query patterns, vocabularies, and…
Diffusion TV: Experiencing Diffusion Models through Tangible, Embodied Interaction
arXiv:2609.05404v1 Announce Type: cross Abstract: Diffusion TV is an interactive AI art installation that offers a tangible and embodied experience of…
Reflection-aware Generative Novel View Synthesis
arXiv:2609.05382v1 Announce Type: cross Abstract: We propose Ref-GeNVS, a training-free, reflection-aware method for generative novel view synthesis (NVS)…