arXiv:2608.09202v1 Announce Type: new Abstract: Modern autonomous vehicles are equipped with multiple sensors, such as cameras, LiDAR, and radar, for…
From Relevance to Execution Utility: Reward-Aware Dynamic Execution Gating for Skill-Based LLM Agents
arXiv:2608.09168v1 Announce Type: new Abstract: Agent skills are increasingly used to equip large language model (LLM) agents with reusable procedural…
AI News Brief Hourly Summary 2026-08-11 23h : 13 posts
13 posts were published in the last hour 20:32 : RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning 20:32 : MELLON – Multimodal Enhanced LLM for Online Navigation 20:32 : CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference…
RISE-RL: Rubric-Informed Selective Exploration for Open-Ended Reinforcement Learning
arXiv:2608.09123v1 Announce Type: new Abstract: Aligning Large Language Models (LLMs) for open-ended tasks is challenging because responses must satisfy…
MELLON – Multimodal Enhanced LLM for Online Navigation
arXiv:2608.09121v1 Announce Type: new Abstract: Web navigation agents are capable of addressing various types of tasks on different websites. Current…
CIDER: A Dataset of Contextual Disclosure Boundaries for Privacy Preference Alignment
arXiv:2608.09164v1 Announce Type: new Abstract: Aligning large language models (LLMs) with human privacy preferences requires capturing individuals’…
TRACE: TRajectory Attribution for Automated Context Engineering
arXiv:2608.09153v1 Announce Type: new Abstract: Production AI agents fail when their context sources — system prompts, knowledge bases, tool…
Quantinuum Puts a 98-Qubit Helios Machine Inside Oracle’s AI Data Centers
Quantinuum and Oracle announced a multi-year strategic partnership on August 11, 2026 that will install Quantinuum’s Helios quantum computer inside a…
ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models
arXiv:2608.09124v1 Announce Type: new Abstract: Temporal decisions in language-model systems often depend on both symbolic task state and elapsed…
Motif 3: Technical Report
arXiv:2608.09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters…
Different Feedback, Different Updates: Selective Self-Learning from User Interactions for Large Language Models
arXiv:2608.09109v1 Announce Type: new Abstract: User feedback offers natural supervision for persistent LLM improvement, but a single message may support…
RAVEN-Eval: Rubric-Guided Automatic Evaluation for AI Video Generation Models Based on LMM Preference Judgement
arXiv:2608.09111v1 Announce Type: new Abstract: AI video generation has advanced rapidly and entered widespread commercial use. As a result, quality…
A Multi-Scale Temporal Framework with Dynamic Fusion for EEG-Based Emotion Recognition
arXiv:2608.09088v1 Announce Type: new Abstract: Mixed emotions represent a clinically relevant but still underexplored target for automatic emotion…
The Video Production Stack Now Fits on One Desk: LTX-2.5 Launches as NVIDIA-Accelerated Open Weights World Model
LTX-2.5 brings frontier video generation to local NVIDIA hardware: 6.8-second clips, native multishot, day-one ComfyUI, open weights.
Who Bridges Safety? Identifying and Targeting Cross-Lingual Shared Safety Pathways
arXiv:2608.09095v1 Announce Type: new Abstract: Uncovering the internal mechanisms underlying the safety capabilities of large language models (LLMs) is…
AI News Brief Hourly Summary 2026-08-11 22h : 16 posts
16 posts were published in the last hour 19:32 : DualCert: A Solver for the Traveling Salesman Problem with Constraint-Coupled Learning 19:32 : ByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Model…
DualCert: A Solver for the Traveling Salesman Problem with Constraint-Coupled Learning
arXiv:2608.09042v1 Announce Type: new Abstract: Large traveling salesman problem (TSP) instances require a solver to allocate limited computation while…
ByteDance Seed Introduces SeedRealtime: a Native Audio-Visual Full-Duplex LLM That Watches, Listens and Speaks in One Model
ByteDance’s Seed team has introduced SeedRealtime, a native audio-visual full-duplex LLM. The model fuses audio, video and text in a single unified…