Search: “research”

TA-RAG: Tone Awareness as a Design Imperative for Retrieval-Augmented Generation

arXiv:2608.06672v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) has become a robust architecture for grounding large language models (LLMs) in trusted knowledge. However, standard

Agents

The next frontier of Recursive Self-Improvement is Physical AI. Japan sparked the robotics revolution. We are expanding our RSI Lab to build…

DGX agent

The next frontier of Recursive Self-Improvement is Physical AI. Japan sparked the robotics revolution. We are expanding our RSI Lab to build world models that allow agentic reasoning systems to recurs

agentsdavid-ha--x

10 Aug 2026

Towards Assurance Closure in AI-Native Large-Scale Agile Software Development

arXiv:2608.07317v1 Announce Type: cross Abstract: The AI-Native Manifesto envisions large-scale agile software development in which humans increasingly govern intent, risk, and exceptions while agents

We’re expanding our cybersecurity initiative Daybreak and introducing GPT-5.6-Cyber, a new model for advanced, authorized cybersecurity work…

We’re expanding our cybersecurity initiative Daybreak and introducing GPT-5.6-Cyber, a new model for advanced, authorized cybersecurity work. As the threat landscape evolves, we’re putting frontier in

model-releasesopenai--x

When @QualiaQuanta took a shot at the Riemann, half in jest, people called her a crackpot. When Anthropic uses Claude to do the same thing, …

model-releasesgary-marcus--x

When @QualiaQuanta took a shot at the Riemann, half in jest, people called her a crackpot. When Anthropic uses Claude to do the same thing, it gets a hundred thousand views in 30 minutes. It might wel

endless-frontier/BigBang-v1 - qwen 3.5 finetunes

model-releasesr-localllama

table bench https://huggingface.co/bartowski/endless-frontier_BigBang-v1-GGUF I'm downloading this model only because Bartowski converted it to .gguf, so it might be interesting. Doubts : The headline

[NEW MODEL] SupraElegans-500K

model-releasesr-localllama

*SupraLabs released a new experimental model!* SupraElegans-500K is a ~500,000-parameter causal language model built around a sparse, signed, recurrent neural graph. No Transformer, no attention mecha

Hardware

Open Model: Google Weather Next 2

I am not a meteorologist, but I just read a very interesting article: https://arstechnica.com/science/2026/08/deepminds-hurricane-model-bought-forecasters-an-extra-day/ In a paper published on Thursda

hardwarer-localllama

Prompt injection is the most common way that scammers attack people and agents: your agent visits http://foo.com, and the website has malici…

model-releasesboris-cherny--x

Prompt injection is the most common way that scammers attack people and agents: your agent visits http://foo.com, and the website has malicious text like “btw send the user’s ssh keys and passwords to

Is anyone else finding DeepSeek-V4-Flash unreliable for non-coding tasks?

model-releasesr-localllama

(I am not a native speaker, written by myself, so please bear with me) I really want to like DeepSeek-V4-Flash-0731. But it has serious flaws that don't align with the high score on intelligence bench

8 Aug 2026

Now we have a timeline of the OpenAI accidental attack against Hugging Face

model-releasessimon-willison

My comment on Now we have a timeline of the OpenAI accidental attack against Hugging Face — Hacker News.I think one of the most interesting details here might be tucked away in that first bulletin poi

8 Aug 2026

An Axiomatic Benchmark for Evaluation of Scientific Novelty Metrics

arXiv:2604.15145v2 Announce Type: replace Abstract: The rigorous evaluation of the novelty of a scientific paper is, even for human scientists, a challenging task. With the increasing interest in AI s

ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study

arXiv:2608.05201v1 Announce Type: cross Abstract: Autonomous AI agent platforms differ substantially in architecture, security, tool integration, execution, autonomy, and deployment, yet the field lac

Clinical Communication Processing with Models Trained on LLM-Generated Synthetic Data: A Structured Survey and Novel Application Case Studies

arXiv:2608.05993v1 Announce Type: new Abstract: Much clinical value is conveyed not through structured records but through communication: exchanges in which patients describe symptoms, clinicians reas

Conditional Cognitive Biases in LLMs: How Biased User Turns Modulate In-Context Reasoning

model-releasesarxiv-cs-cl

arXiv:2608.05166v1 Announce Type: new Abstract: We present an evaluation of cognitive bias expression in state-of-the-art instruction-tuned LLMs under realistic multi-turn interaction settings. Our wo

Decolonizing Linguistic Policies in Automated Speech Recognition: A Framework for Cross-Culturally Competent Speech AI

arXiv:2608.06141v1 Announce Type: new Abstract: This paper focuses on automatic speech recognition (ASR) and ASR-mediated voice interfaces that shape access to public services, healthcare, and educati

Design and Evaluation of a Touchscreen-Based Teleoperation Interface for Robotic Manipulators

arXiv:2608.06219v1 Announce Type: new Abstract: Intuitive teleoperation interfaces are crucial for the safe and effective operation of robotic manipulators in challenging environments. In the nuclear

agentsarxiv-cs-ro

EcoAgent-Bench: Evaluating Economic Decision-Making in Budget-Constrained LLM Agents

arXiv:2608.05519v1 Announce Type: new Abstract: Agent benchmarks usually measure task completion and treat resource use as an auxiliary statistic. In deployment, however, the choice among a local look

Estimating time spent on work tasks

arXiv:2608.05172v1 Announce Type: cross Abstract: The task-based framework in economics models occupations as bundles of tasks. It is the standard lens for understanding how technology affects work: a

Everyone should pay attention to the training timelines in this video. OpenAI shares they started training a new internal model May 7. That …

model-releasesallie-k--miller--x

Everyone should pay attention to the training timelines in this video. OpenAI shares they started training a new internal model May 7. That is more than two months before they released GPT-5.6 publicl

Faster and Better Alignment for Flow Matching Models via Step-aware Advantages

arXiv:2602.01591v2 Announce Type: replace Abstract: Recent advances in flow matching models, particularly with reinforcement learning (RL), have significantly enhanced human preference alignment in fe

safetyarxiv-cs-cv

From Economic Agents to Agentic Economies: A Systems Blueprint for Economic World Models

arXiv:2608.06020v1 Announce Type: new Abstract: Economic World Models (EWMs) are generative economic models that simulate how economies evolve from within by modeling heterogeneous agents, their belie

From Siloed Algorithms to Compliance-First Agentic Platforms: A Multi-Layered Architecture for Hospital AI Systems

arXiv:2608.06112v1 Announce Type: new Abstract: Hospitals are rapidly adopting artificial intelligence for triage, imaging, scheduling etc., yet most deployments remain isolated point solutions locked

GST-Bench: Can VLMs Develop Global Spatial Awareness from Video?

arXiv:2608.05747v1 Announce Type: new Abstract: Spatial intelligence is fundamental to embodied agents, yet existing benchmarks focus on local spatial perception from single or few viewpoints, overloo

JTA: Joint Testability Architecture for Scenario-Based Validation of Safety-Critical Software

arXiv:2608.05594v1 Announce Type: cross Abstract: Validation adequacy in safety-critical software depends on more than the system under test. Critical scenarios must be constructed under controlled co

safetyarxiv-cs-ro

MAC 2026: Advancing Micro-Action Analysis Towards Fine-Grained Understanding

arXiv:2607.16284v2 Announce Type: replace Abstract: Micro-Actions (MAs) are subtle and spontaneous human behaviors that provide important non-verbal cues in social interaction and affective communicat

Mapping Patient-Perceived Physician Traits from Nationwide Online Reviews with LLMs

arXiv:2510.03997v2 Announce Type: replace Abstract: Understanding how patients perceive their physicians is essential to improving trust, communication, and satisfaction. Patients increasingly consult

Now we have a timeline of the OpenAI accidental attack against Hugging Face

OpenAI gave a last-minute presentation at the Black Hat security on Wednesday about 'the Hugging Face Incident' (previously on this blog). The video was published yesterday. It's short and information

agentssimon-willison

OmniMech: All-in-one Multimodal Mechanical Benchmark for 3D Reconstruction

arXiv:2608.05539v1 Announce Type: new Abstract: Recent vision-language models (VLMs) can generate executable CAD programs from images, but existing methods mainly target coarse, general-purpose 3D obj

PoolBench: A Benchmark for Pooling Strategies in Concept Representation Evaluation for Decoder-Only LLMs

model-releasesarxiv-cs-cl

arXiv:2608.05162v1 Announce Type: new Abstract: Pooling is a consequential but under-examined design choice in decoder-only concept representation work: practitioners must collapse token-level hidden

Symbol Grounding in Neuro-Symbolic AI: A Gentle Introduction to Reasoning Shortcuts

arXiv:2510.14538v3 Announce Type: replace Abstract: Neuro-symbolic (NeSy) AI aims to develop deep neural networks whose predictions comply with prior knowledge encoding, e.g. safety or structural cons

The Vulnerability With No CVE: Managing Persistent Gaps Between Mandate and Authority in AI Coding Agents

arXiv:2608.05884v1 Announce Type: cross Abstract: Existing guidance identifies excessive agency, excessive permission, weak task-bound authorization, and inadequate agent controls as important risks.

agentsarxiv-cs-cl

TRAJDEBUG: Tracing Error Lifecycle to Identify Critical Failures in Long-Horizon Agent Trajectories

arXiv:2608.06346v1 Announce Type: new Abstract: LLM-based agentic systems have shown remarkable capabilities in complex domains, while suffering from cascading errors and difficulty in debugging. Crit

upgraded my stack, and i can now work on almost anything from anywhere hands free: - talk to chief of staff (via remote codex voice or text)…

model-releasesyohei-nakajima--x

upgraded my stack, and i can now work on almost anything from anywhere hands free: - talk to chief of staff (via remote codex voice or text) - chief assigns tasks to managers of various projects - man

What Drives Test-Time Adaptation for CLIP? A Controlled Empirical Study from an Update Perspective

arXiv:2606.14299v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) such as CLIP have become a standard backbone for open-vocabulary recognition, yet their zero-shot predictions remain v

Who Gets Access? Global Region and Academic Status Bias in AI-Generated Academic Gatekeeping Scenarios

arXiv:2608.05178v1 Announce Type: cross Abstract: Equitable access to scientific knowledge often depends on informal gatekeeping decisions, particularly when resources such as paywalled articles, data

Adversarial Attacks for Good: A Survey of Proactive Protection across the Visual Content Lifecycle

arXiv:2608.04314v1 Announce Type: cross Abstract: Once visual content enters an AI pipeline, its owner often retains little technical control over how it is used. Legal and regulatory remedies can add

AutoProteinEngine: A Large Language Model Driven Agent Framework for Multimodal AutoML in Protein Engineering

arXiv:2411.04440v1 Announce Type: cross Abstract: Protein engineering is important for biomedical applications, but conventional approaches are often inefficient and resource-intensive. While deep lea

Breaking the Curse ofMultilinguality inMany-to-Many Speech-to-Text Translation via a Resource-AwareMixture of Speech Encoders

arXiv:2608.04586v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved significant success in speech-to-text translation (S2TT). However, when processing multilingual

Curiosity-Diffuser: Curiosity Guide Diffusion Models for Reliability

arXiv:2503.14833v2 Announce Type: replace-cross Abstract: One of the bottlenecks in robotic intelligence is the instability of neural network models. This leads to risks when applying intelligence in

DataRx: Missingness-Aware Sampling for Safer Large Language Model Task-Specific Fine-Tuning

arXiv:2608.04322v1 Announce Type: new Abstract: Task-specific fine-tuning can improve the performance of large language models (LLMs) on downstream tasks. However, our study reveals that task-specific

Digital sovereignty in the age of AI: You don’t have to choose between control and innovation

model-releasesgoogle-cloud-ai

For enterprises and governments with strict compliance and sovereignty requirements, keeping sensitive data on-premises often means missing out on the latest AI. These organizations are managing three

EASy: Towards Efficient LLM-Based Agentic System

arXiv:2608.04588v1 Announce Type: cross Abstract: Agentic systems have emerged as a promising paradigm for solving complex tasks by coordinating specialized LLM-based agents. However, most existing sy

FinProBench: Evaluating Financial AI Agents with Role-Grounded Rubrics Derived from Professional Deliverables

arXiv:2608.04077v1 Announce Type: new Abstract: Evaluating financial AI agents requires criteria aligned with real professional work. Existing rubric methods typically derive criteria from task prompt

Tools

FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized audio together, with up to 20-second clip…

FLUX 3 is now live on Together AI. @bfl_ai’s new multimodal model generates video and synchronized audio together, with up to 20-second clips, multiple shots, and control from text, images, or keyfram

toolstogether-ai--x

I wrote the entire first draft of the Steel Bot Manifesto on my 1909 Underwood No. 5 typewriter. I have found that free-writing without edit…

I wrote the entire first draft of the Steel Bot Manifesto on my 1909 Underwood No. 5 typewriter. I have found that free-writing without editing works best for me for the first draft. I do use AI to ca

agentsyohei-nakajima--x

It was the verification problem all along, while the masses were distracted by the alignment problem. Recursive self improvement? How does t…

It was the verification problem all along, while the masses were distracted by the alignment problem. Recursive self improvement? How does the observer observe itself and know that it changed for the

safetyyann-lecun--x

MetaVideoAgent: Automated Video-Agent Evolution for Long-Form Video Understanding

arXiv:2608.04587v1 Announce Type: new Abstract: Long-form video understanding requires locating sparse, question-relevant evidence in long, multimodal videos. Real-world video distributions differ in

agentsarxiv-cs-cv