NAVI-Orbital: First In-Orbit Demonstration of a Zero-Shot Vision-Language Model for Autonomous Earth Observation
arXiv:2606.18271v1 Announce Type: new Abstract: As Earth Observation data generation outpaces downlink bandwidth and human-in-the-loop processing, a widening gap has emerged bet...
CaVe-VLM-CoT: An Interpretable Vision-Language Model Framework
arXiv:2606.18385v1 Announce Type: new Abstract: Vision-Language Models (VLMs) remain prone to hallucinations, producing fluent but visually unfaithful outputs. Existing chain-of...
CEO-Bench: Can Agents Play the Long Game?
arXiv:2606.18543v1 Announce Type: new Abstract: Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and custome...
SproutRAG: Attention-Guided Tree Search with Progressive Embeddings for Long-Document RAG
arXiv:2606.18381v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) systems must balance retrieval granularity with contextual coherence, a challenge that exist...
JetFlow: Breaking the Scaling Ceiling of Speculative Decoding with Parallel Tree Drafting
arXiv:2606.18394v1 Announce Type: new Abstract: Speculative decoding (SD) accelerates autoregressive Large Language Models (LLMs) by drafting multiple tokens and verifying them...
VISUALSKILL: Multimodal Skills for Computer-Use Agents
arXiv:2606.18448v1 Announce Type: new Abstract: Computer-use agents (CUAs) approach human-level performance on standardised benchmarks but still struggle on long-horizon tasks a...
Is it agentic enough? Benchmarking open models on your own tooling
Is it agentic enough? Benchmarking open models on your own tooling
Predicting model behavior before release by simulating deployment
OpenAI introduces Deployment Simulation, a method to predict AI model behavior before deployment using real conversation data to improve safety and evaluation accuracy.
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.
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
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.
Intelica – competitive intelligence API that charges AI agents $0.05 via x402
Article URL: https://api.intelica.dev Comments URL: https://news.ycombinator.com/item?id=48592817 Points: 1 # Comments: 0
Show HN: OSymandias – Open-source runtime for multi-agent AI systems
Article URL: https://github.com/andreisilva1/OSymandias Comments URL: https://news.ycombinator.com/item?id=48591144 Points: 3 # Comments: 1
Show HN: Open-source back end for multi-user AI agents with shared memory
Article URL: https://github.com/lobu-ai/lobu Comments URL: https://news.ycombinator.com/item?id=48590973 Points: 2 # Comments: 0
A New Framework for Evaluating Voice Agents (EVA)
A New Framework for Evaluating Voice Agents (EVA)
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.
DeFAb: A Verifiable Benchmark for Defeasible Abduction in Foundation Models
arXiv:2606.18557v1 Announce Type: new Abstract: A rule-based logic solver resolves every instance in our benchmark in under 50 microseconds with 100% accuracy; the best frontier...
ForecastBench-Sim: A Simulated-World Forecasting Benchmark
arXiv:2606.18686v1 Announce Type: new Abstract: Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly,...