arXiv:2608.07023v1 Announce Type: cross Abstract: Organizing thousands of unstandardized, multilingual expertise declarations is a persistent challenge…
Beyond Text Matching: Towards Reference-Free Evaluation for Human-Oriented Binary Reverse Engineering
arXiv:2608.07038v1 Announce Type: cross Abstract: Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more…
AI News Brief Hourly Summary 2026-08-10 21h : 15 posts
15 posts were published in the last hour 18:32 : Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents 18:32 : PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue 18:32 : Expanding Daybreak as the…
Same physical state, different collective dynamics: state encodings select synchronization outcomes in language-model agents
arXiv:2608.06968v1 Announce Type: cross Abstract: Language-model agents act on state encodings of their environment, yet these are treated as…
PHASE-Tree: Modeling Character-State Evolution in Long-Horizon Role-Playing Dialogue
arXiv:2608.06975v1 Announce Type: cross Abstract: Long-horizon role-playing demands that characters remain recognizable as they evolve with the narrative.…
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…
HarnessSafe: Evaluating Safety Across Persistent Carriers in Agent Harnesses
arXiv:2608.06984v1 Announce Type: cross Abstract: Modern agent harnesses persist state across tasks and sessions through persistent carriers like memory,…
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,…
Density-aware Hierarchical Clustering Based on Element-Categorized Connection Subgraphs
arXiv:2608.06990v1 Announce Type: cross Abstract: Clustering is a fundamental data mining technique for pattern recognition through unsupervised learning.…
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…
GPTKB 2.0: Browsing, Querying, and Auditing a Disambiguated LLM-Derived Knowledge Base
arXiv:2608.06992v1 Announce Type: cross Abstract: We present a web demo for exploring a large-scale disambiguated knowledge base (KB) materialized from a…
Debias in Text, Believe Your Eyes: Text-Anchored Cross-Modal Transfer for Visual Counter-Commonsense Reasoning
arXiv:2608.06938v1 Announce Type: cross Abstract: The visual reasoning ability of multimodal large language models (MLLMs) is crucial for downstream…
Ask-E: An Environment for Calibrated Question Generation
arXiv:2608.06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities.…
MaskFlow: Precise, Consistent and Seamless Regional Image Editing
arXiv:2608.06929v1 Announce Type: cross Abstract: Regional image editing has attracted considerable attention for its spatial controllability. Although…
Explicit, Not Longer: What Makes Epistemic Stance Survive Memory Compression
arXiv:2608.06953v1 Announce Type: cross Abstract: Agent memory systems compress what they store, and compression is built to drop qualifiers, so a claim’s…
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…
Calibrating WEAT Against Anisotropy: ZCA Whitening as a Geometric Pre-Processing Step for Embedding Association Tests
arXiv:2608.06908v1 Announce Type: cross Abstract: We propose Zero-phase Component Analysis (ZCA) whitening as a geometric pre-processing step for the Word…
AI News Brief Hourly Summary 2026-08-10 20h : 17 posts
17 posts were published in the last hour 17:33 : Bridging the Gap Between Hyperdimensional Computing and Kernel Methods via the Nystr\”om Method 17:33 : Putting frontier cyber models in more trusted hands 17:33 : Multi-Agent Forensic Reasoning for Generalizable…