GATS: Graph-Augmented Tree Search with Layered World Models for Efficient Agent Planning
arXiv:2607.08894v1 Announce Type: new Abstract: Large Language Model (LLM) agents have shown promise in multi-step planning tasks, but existing approaches like LATS (Language Ag...
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading
arXiv:2607.08964v1 Announce Type: new Abstract: AI agents have become capable of autonomously completing short, well-specified tasks. However, existing terminal benchmarks large...
ARCANA: A Reflective Multi-Agent Program Synthesis Framework for ARC-AGI-2 Reasoning
arXiv:2607.09059v1 Announce Type: new Abstract: We present ARCANA, a collaborative multi agent framework for solving ARC AGI 2 tasks under strict test time and hardware constrai...
An Emergent Mirage: Is Emergent Misalignment and Realignment Indeed a Robust Phenomenon?
arXiv:2607.09053v1 Announce Type: new Abstract: Recent work has reported Emergent Misalignment (EM), where language models fine-tuned on narrow, domain-specific misaligned datas...
AgentKGV: Agentic LLM-RAG Framework with Two-Stage Training for the Fact Verification of Knowledge Graphs
arXiv:2607.09092v1 Announce Type: new Abstract: Knowledge graphs (KGs) are often automatically constructed from large-scale corpora, but they inevitably contain factual errors d...
FreyaTTS Technical Report
arXiv:2607.09530v1 Announce Type: new Abstract: We introduce Freya-TTS, a compact, tokenizer-free, Turkish-first text-to-speech model designed for highly reliable and efficient...
OpenAI frontier models and Codex are now available on AWS
OpenAI frontier models and Codex are now generally available on AWS, giving enterprises a new path to build with OpenAI through the AWS environments, controls, and procurement w...
Databricks brings GPT-5.5 to enterprise agent workflows
Databricks uses GPT-5.5 for enterprise agent workflows after the model set a new state of the art on the OfficeQA Pro benchmark.
Introducing GPT-5.4 mini and nano
GPT-5.4 mini and nano are smaller, faster versions of GPT-5.4 optimized for coding, tool use, multimodal reasoning, and high-volume API and sub-agent workloads.
MIT's New Method Flags AI Models Trained on CASM Without Generating It
Article URL: https://insideai.news/news/ai-safety/mits-new-method-flags-ai-models-trained-on-child-abuse-imagery-without-generating-it/3869/ Comments URL: https://news.ycombinat...
CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models
CyberSecEval 2 - A Comprehensive Evaluation Framework for Cybersecurity Risks and Capabilities of Large Language Models
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
ScarfBench: Benchmarking AI Agents for Enterprise Java Framework Migration
Introducing the Gemini 2.5 Computer Use model
Available in preview via the API, our Computer Use model is a specialized model built on Gemini 2.5 Pro’s capabilities to power agents that can interact with user interfaces.
Karios AI Agent Carzy
Article URL: https://github.com/adnqcr7-code/kairosv2 Comments URL: https://news.ycombinator.com/item?id=48899535 Points: 2 # Comments: 0
Is it agentic enough? Benchmarking open models on your own tooling
Is it agentic enough? Benchmarking open models on your own tooling
ORA – AI coding agent that blocks its own commits if security scan fails
Article URL: https://auremcto.com/ Comments URL: https://news.ycombinator.com/item?id=48899930 Points: 1 # Comments: 0
Gemma Scope 2: helping the AI safety community deepen understanding of complex language model behavior
Open interpretability tools for language models are now available across the entire Gemma 3 family with the release of Gemma Scope 2.
Strengthening our Frontier Safety Framework
We’re strengthening the Frontier Safety Framework (FSF) to help identify and mitigate severe risks from advanced AI models.
Neuro-Agentic Control: A Deep Learning-based LLM-Powered Agentic AI Framework for Controlling Security Controls
arXiv:2607.09076v1 Announce Type: new Abstract: Cyberattacks on operational technology are increasingly causing costly downtime and physical damage, exposing the limitations of...
L-MAD: A Systematic Evaluation of Multi-Agent Debate Structures in Legal Reasoning
arXiv:2607.09099v1 Announce Type: new Abstract: While multi-agent debate (MAD) frameworks have shown significant potential in general reasoning, their effectiveness in highly st...