CohortFlow: A Steerable Clinical Cohort Curation Agent with Localized Semantic Correction
arXiv:2610.36100v1 Announce Type: new
Abstract: Language model agents for clinical cohort curation should accommodate evolving eligibility criteria without repeatedly processing unchanged requirements. We introduce CohortFlow, a steerable agent that represents natural language corrections as locali...
The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents
arXiv:2610.36077v1 Announce Type: new
Abstract: Multimodal intelligence can be viewed as human-guided co-evolution between worlds and agents through interaction. However, scaling this process faces two bottlenecks: constructing heterogeneous, verifiable environments is costly, and manual Harness it...
Enhancing Deep Learning Model Performance through Data Generation Strategies: Classification of Olive Tree Diseases
arXiv:2610.35984v1 Announce Type: new
Abstract: Deep learning models are highly effective in a wide range of domains, particu larly in plant disease diagnosis. However, their performance is often limited by challenges such as insufficient data and class imbalance. In our work, we propose a comprehe...
Inference-Time Prior Adaptation for Imbalanced Data Streams under Concept Drift
arXiv:2610.33126v1 Announce Type: new
Abstract: Data stream classification under concept drift and class imbalance requires models to adapt continuously while maintaining strong minority-class performance. Many existing approaches rely on active memory management, in- cluding instance removal, memo...
Feature Scaling Beats Architecture Choice in Offline Respiratory Screening for Low-Resource Clinics
arXiv:2610.33030v1 Announce Type: new
Abstract: Deep models are the usual choice for respiratory sound classification, but in clinics without GPUs or connectivity that choice carries a cost. We compare classical and deep classifiers on a five-class respiratory-sound corpus of 1,211 clips (asthma, C...
Lessons from Luck: Do LLM-Written Lessons Carry Chance into an Agent's Next Decision?
arXiv:2610.33029v1 Announce Type: new
Abstract: Self-improving agents write lessons from the outcomes of their runs; when outcomes are noisy, a lesson can carry chance into later decisions. We measure one link of this chain in a registered study. In 256 synthetic worlds, each a recurring task with ...
Can Language Models Learn While They Think? Testing Gradient Adaptation Across Architectures
arXiv:2610.33025v1 Announce Type: new
Abstract: Letting a language model take gradient steps on the text it is reading, known as dynamic evaluation, lowers its loss on the rest of the document. Its behaviour on hybrid linear-attention architectures, on diffusion language models, and on standard lon...
Evolving to Match Capabilities: Improving Harness Self-Evolution via Skill Adaptation
arXiv:2610.33024v1 Announce Type: new
Abstract: Harness self-evolution offers a practical route for LLM agents to improve from execution experience without updating model parameters. Its effectiveness depends on whether models can successfully act on the guidance provided by their harnesses. Howeve...
Parents sue OpenAI, alleging GPT-4o coached their daughter off seizure medication
A family is suing OpenAI, saying ChatGPT coached their daughter to quietly taper off her seizure medication and keep it from her doctors before she died in February.
Liquid AI Releases LFM3: 6 Open-Weight 2B-Class Multimodal Models
Liquid AI released LFM3, 6 open-weight 2B-class models for text, vision, audio, omni and decisions. LFM3-1.7B uses a tri-hybrid backbone, a 256K context window and fits in about 1 GB at 4-bit.
The post Liquid AI Releases LFM3: 6 Open-Weight 2B-Class Multimodal Models appeared first on MarkTechPost.
DailyAI Briefing: AI breaks a computing rule, plus 4 more
OpenAI and Anthropic both say AI disproved a decades-old computer science rule, and the FTC wants Anthropic's executives under oath.
Plus Qwen tries to phone Beijing, Siri gets a memory, and ChatGPT turns election fakes into cartoons.
The post DailyAI Briefing: AI breaks a computing rule, plus 4 mor...
Google’s Genie 4 world model adds audio, more realistic worlds, and real-time steering
Google DeepMind released Genie 4, a world model with real-time audio, more realistic simulations, and mid-simulation text prompts, in research preview for trusted testers.
I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It
I replayed correct model decisions through four broken browser actions. A simple page check missed half of the wrong clicks, and raised a false alarm on every click that worked inside an embedded page.
The post I Broke a Browser Agent on Purpose. Spotting the Fault Was Not the Same as Fixing It appe...
Meta AI director Rohit Patel leaves to take on Microsoft Office and Google Workspace
Rohit Patel is departing Meta after eight years working on AI evaluations and reinforcement learning, TechCrunch has exclusively learned. His startup, Ndoc, aims to take on Microsoft Office Suite.
OpenAI and Anthropic Say AI Broke the Same Computer Science Rule
Both labs say their AI models disproved the Exponential Time Hypothesis on the same day, 16 October. Outside experts are now checking, and Anthropic says the gain only shows up beyond 10 million variables.
The post OpenAI and Anthropic Say AI Broke the Same Computer Science Rule appeared first on Da...
Toronto pairs Hinton-era research depth with bank-sized AI budgets. Here is where the city's biggest AI players are building, and what they are shipping.