arXiv:2608.10492v1 Announce Type: new Abstract: Large Language Model (LLM)-based simulators often reproduce observable actions but fail to capture the…
From Faulty Memories to Corrected Actions: Dependency-Guided Rollback Repair for Memory-Augmented Agents
arXiv:2608.10502v1 Announce Type: new Abstract: Persistent memory lets language-model agents reuse information across sessions, but it also makes errors…
RadFusion: Towards Threshold-Controllable Radiology Report Generation
arXiv:2608.10505v1 Announce Type: new Abstract: Automated radiology report generation is advancing rapidly in response to the shortage of radiologists,…
MEGA: Self-Evolving Agent Optimization Infrastructure via Wisdom Graph
arXiv:2608.10504v1 Announce Type: new Abstract: As coding agents increasingly handle implementation, the central challenge shifts from building individual…
GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning
arXiv:2608.10494v1 Announce Type: new Abstract: Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions…
AI News Brief Hourly Summary 2026-08-12 10h : 18 posts
18 posts were published in the last hour 7:32 : RLMOpt: Adaptive Prompt Optimization via Recursive Language Models 7:32 : Expanding Daybreak as the Cyber Defense Window Narrows 7:32 : Multi-Granular Rationale-Guided Molecular LLM for Property Prediction 7:32 : Old…
RLMOpt: Adaptive Prompt Optimization via Recursive Language Models
arXiv:2608.10471v1 Announce Type: new Abstract: Prompt optimizers automate the search for prompts that improve language-model performance, but existing…
Expanding Daybreak as the Cyber Defense Window Narrows
Meet GPT-5.6-Cyber, OpenAI’s cybersecurity-specific model available through Daybreak Red for authorized vulnerability research, exploit validation, and…
Multi-Granular Rationale-Guided Molecular LLM for Property Prediction
arXiv:2608.10480v1 Announce Type: new Abstract: Large language models (LLMs) are widely applied across chemical tasks, such as molecular property…
Old OCR text cripples language model training, and FineBooks wants to fix that at scale
The FineBooks project from Hugging Face and EleutherAI tested 14 open-source OCR models on more than 2,000 historical book pages. The top model,…
Evaluating Rational Contracting in Natural Language
arXiv:2608.10475v1 Announce Type: new Abstract: The emergence of language-based AI agents promises to transform the scope of machine economic activity.…
Ryanair Adopts Gemini Enterprise Across Crew Logistics and Flight Operations
Ryanair, Europe’s largest airline, and Google Cloud announced a five-year partnership on August 12, 2026, under which the carrier will deploy Google…
Quantum Incremental Learning with Mixed State Prototypes
arXiv:2608.10464v1 Announce Type: new Abstract: Incremental learning models are required to learn new classes sequentially without catastrophic…
OpenAI Expands Daybreak With Two Tiers and a New Cybersecurity Model
OpenAI is splitting its cybersecurity program into two access tiers and releasing a new purpose-trained model alongside them, the company announced on…
Predicting Space Groups of Double Perovskites by LLM with Dynamic Few-Shot Learning
arXiv:2608.10483v1 Announce Type: new Abstract: Double perovskites (DPs) offer broad compositional tunability, but predicting the space groups (SGs) of…
Recovering Wasted Compute in Autoresearch Agents
arXiv:2608.10424v1 Announce Type: new Abstract: A slew of recent works develop agents for solving research problems end-to-end, a paradigm increasingly…
Rationale-Guided Learning for Multimodal Emotion Recognition
arXiv:2608.10448v1 Announce Type: new Abstract: Multimodal emotion recognition in conversation (MERC) requires understanding complex interactions between…
OpenAI launches GPT-5.6-Cyber to help defenders find vulnerabilities before attackers do
OpenAI aims to give cybersecurity defenders a head start: The new GPT-5.6-Cyber model answers up to 98.5 percent of security queries that would otherwise…