ARCHIVE · 20 SIGNALS Generated: 2026-06-17 10:55
#01

Beyond Parallel Sampling: Diverse Query Initialization for Agentic Search

arXiv:2606.17209v1 Announce Type: new Abstract: Test-time scaling for agentic search typically increases depth (i.e., more turns and tokens per trajectory) or breadth (i.e., mor...

arXiv AI /
#02

When Rules Learn: A Self-Evolving Agent for Legal Case Retrieval

arXiv:2606.17220v1 Announce Type: new Abstract: Legal case retrieval remains challenging due to the complexity of legal language and the need for precise lexical alignment betwe...

arXiv AI /
#03

SkillChain-Gym: A Benchmark for Reskilling-Aware Production-Inventory Control under Disruptions

arXiv:2606.17266v1 Announce Type: new Abstract: Production planning increasingly has to treat workforce capability as a decision variable: certifications lapse when skills are n...

arXiv AI /
#04

MemSlides: A Hierarchical Memory Driven Agent Framework for Personalized Slide Generation with Multi-turn Local Revision

arXiv:2606.17162v1 Announce Type: new Abstract: Personalized presentation generation requires more than conditioning on a current prompt or template: agents must preserve stable...

arXiv Computation and Language /
#05

Self-Generated Error Training for Token Editing in Diffusion Language Models

arXiv:2606.17175v1 Announce Type: new Abstract: Token-to-token (T2T) editing lets LLaDA2.1 revise committed tokens during block-diffusion decoding. The released recipe trains th...

arXiv Computation and Language /
#06

Revisiting LLM Adaptation for 3D CT Report Generation: A Study of Scaling and Diagnostic Priors

arXiv:2606.17213v1 Announce Type: new Abstract: Recent advances in multimodal learning, including large language models (LLMs) and vision-language models (VLMs), have demonstrat...

arXiv Computation and Language /
#07

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 News /
#08

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...

OpenAI News /
#09

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.

OpenAI News /
#10

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

Hugging Face Blog /
#11

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.

Google DeepMind Blog /
#12

Which AI agent spent the money on your OpenAI/Anthropic bill

Article URL: https://github.com/Nu11P01nt3r3xc3pt10n/spaturzu-sdks Comments URL: https://news.ycombinator.com/item?id=48567889 Points: 1 # Comments: 0

Hacker News AI /
#13

A New Framework for Evaluating Voice Agents (EVA)

A New Framework for Evaluating Voice Agents (EVA)

Hugging Face Blog /
#14

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

Beyond LLMs: Why Scalable Enterprise AI Adoption Depends on Agent Logic

Hugging Face Blog /
#15

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.

Google DeepMind Blog /
#16

Strengthening our Frontier Safety Framework

We’re strengthening the Frontier Safety Framework (FSF) to help identify and mitigate severe risks from advanced AI models.

Google DeepMind Blog /
#17

Ask HN: Does your mind drift while waiting for AI prompts to finish?

I've been a software engineer for 9 years now, and I noticed a very new weirdness in my workflows. Once I finish the architecture of a project and i have my context engineering...

Hacker News AI /
#18

Building an AI Agent in 6 Weeks (and Understanding How They Work)

Article URL: https://belderbos.dev/blog/jeff-haemer-agentic-ai-cohort/ Comments URL: https://news.ycombinator.com/item?id=48567620 Points: 1 # Comments: 0

Hacker News AI /
#19

Skill-Constrained Model Predictive Control for Resilient Manufacturing Supply Chains

arXiv:2606.17269v1 Announce Type: new Abstract: In skill-constrained production-inventory systems, the qualified human capacity available tomorrow depends on training decisions...

arXiv AI /
#20

Quantifying Consistency in LLM Logical Reasoning via Structural Uncertainty

arXiv:2606.17312v1 Announce Type: new Abstract: Large language models can arrive at the same answer through reasoning paths that are unstable, contradictory, or difficult to ran...

arXiv AI /