Microsoft ‘Promptions’ fix AI prompts failing to deliverAI News Microsoft believes it has a fix for AI prompts being given, the response missing the mark, and the cycle repeating. This inefficiency is a drain on resources. The “trial-and-error loop can feel unpredictable and discouraging,” turning what should be a productivity booster into a time sink. Knowledge workers often spend more time managing the interaction
The post Microsoft ‘Promptions’ fix AI prompts failing to deliver appeared first on AI News.
Microsoft believes it has a fix for AI prompts being given, the response missing the mark, and the cycle repeating. This inefficiency is a drain on resources. The “trial-and-error loop can feel unpredictable and discouraging,” turning what should be a productivity booster into a time sink. Knowledge workers often spend more time managing the interaction
The post Microsoft ‘Promptions’ fix AI prompts failing to deliver appeared first on AI News. Read More
7 Pandas Performance Tricks Every Data Scientist Should KnowTowards Data Science What I’ve learned about making Pandas faster after too many slow notebooks and frozen sessions
The post 7 Pandas Performance Tricks Every Data Scientist Should Know appeared first on Towards Data Science.
What I’ve learned about making Pandas faster after too many slow notebooks and frozen sessions
The post 7 Pandas Performance Tricks Every Data Scientist Should Know appeared first on Towards Data Science. Read More
How Agent Handoffs Work in Multi-Agent SystemsTowards Data Science Understanding how LLM agents transfer control to each other in a multi-agent system with LangGraph
The post How Agent Handoffs Work in Multi-Agent Systems appeared first on Towards Data Science.
Understanding how LLM agents transfer control to each other in a multi-agent system with LangGraph
The post How Agent Handoffs Work in Multi-Agent Systems appeared first on Towards Data Science. Read More
OpenAI Introduces GPT 5.2: A Long Context Workhorse For Agents, Coding And Knowledge WorkMarkTechPost OpenAI has just introduced GPT-5.2, its most advanced frontier model for professional work and long running agents, and is rolling it out across ChatGPT and the API. GPT-5.2 is a family of three variants. In ChatGPT, users see ChatGPT-5.2 Instant, Thinking and Pro. In the API, the corresponding models are gpt-5.2-chat-latest, gpt-5.2, and gpt-5.2-pro. Instant
The post OpenAI Introduces GPT 5.2: A Long Context Workhorse For Agents, Coding And Knowledge Work appeared first on MarkTechPost.
OpenAI has just introduced GPT-5.2, its most advanced frontier model for professional work and long running agents, and is rolling it out across ChatGPT and the API. GPT-5.2 is a family of three variants. In ChatGPT, users see ChatGPT-5.2 Instant, Thinking and Pro. In the API, the corresponding models are gpt-5.2-chat-latest, gpt-5.2, and gpt-5.2-pro. Instant
The post OpenAI Introduces GPT 5.2: A Long Context Workhorse For Agents, Coding And Knowledge Work appeared first on MarkTechPost. Read More
CopilotKit v1.50 Brings AG-UI Agents Directly Into Your App With the New useAgent HookMarkTechPost Agent frameworks are now good at reasoning and tools, but most teams still write custom code to turn agent graphs into robust user interfaces with shared state, streaming output and interrupts. CopilotKit targets this last mile. It is an open source framework for building AI copilots and in-app agents directly in your app, with real
The post CopilotKit v1.50 Brings AG-UI Agents Directly Into Your App With the New useAgent Hook appeared first on MarkTechPost.
Agent frameworks are now good at reasoning and tools, but most teams still write custom code to turn agent graphs into robust user interfaces with shared state, streaming output and interrupts. CopilotKit targets this last mile. It is an open source framework for building AI copilots and in-app agents directly in your app, with real
The post CopilotKit v1.50 Brings AG-UI Agents Directly Into Your App With the New useAgent Hook appeared first on MarkTechPost. Read More
Grounding the Ungrounded: A Spectral-Graph Framework for Quantifying Hallucinations in Multimodal LLMscs.AI updates on arXiv.org arXiv:2508.19366v4 Announce Type: replace-cross
Abstract: Hallucinations in LLMs–especially in multimodal settings–undermine reliability. We present a rigorous information-geometric framework, grounded in diffusion dynamics, to quantify hallucinations in MLLMs where model outputs are embedded via spectral decompositions of multimodal graph Laplacians, and their gaps to a truth manifold define a semantic distortion metric. We derive Courant-Fischer bounds on a temperature-dependent hallucination profile and use RKHS eigenmodes to obtain modality-aware, interpretable measures that track evolution over prompts and time. This reframes hallucination as quantifiable and bounded, providing a principled basis for evaluation and mitigation.
arXiv:2508.19366v4 Announce Type: replace-cross
Abstract: Hallucinations in LLMs–especially in multimodal settings–undermine reliability. We present a rigorous information-geometric framework, grounded in diffusion dynamics, to quantify hallucinations in MLLMs where model outputs are embedded via spectral decompositions of multimodal graph Laplacians, and their gaps to a truth manifold define a semantic distortion metric. We derive Courant-Fischer bounds on a temperature-dependent hallucination profile and use RKHS eigenmodes to obtain modality-aware, interpretable measures that track evolution over prompts and time. This reframes hallucination as quantifiable and bounded, providing a principled basis for evaluation and mitigation. Read More
Cytoplasmic Strings Analysis in Human Embryo Time-Lapse Videos using Deep Learning Frameworkcs.AI updates on arXiv.org arXiv:2512.09461v1 Announce Type: cross
Abstract: Infertility is a major global health issue, and while in-vitro fertilization has improved treatment outcomes, embryo selection remains a critical bottleneck. Time-lapse imaging enables continuous, non-invasive monitoring of embryo development, yet most automated assessment methods rely solely on conventional morphokinetic features and overlook emerging biomarkers. Cytoplasmic Strings, thin filamentous structures connecting the inner cell mass and trophectoderm in expanded blastocysts, have been associated with faster blastocyst formation, higher blastocyst grades, and improved viability. However, CS assessment currently depends on manual visual inspection, which is labor-intensive, subjective, and severely affected by detection and subtle visual appearance. In this work, we present, to the best of our knowledge, the first computational framework for CS analysis in human IVF embryos. We first design a human-in-the-loop annotation pipeline to curate a biologically validated CS dataset from TLI videos, comprising 13,568 frames with highly sparse CS-positive instances. Building on this dataset, we propose a two-stage deep learning framework that (i) classifies CS presence at the frame level and (ii) localizes CS regions in positive cases. To address severe imbalance and feature uncertainty, we introduce the Novel Uncertainty-aware Contractive Embedding (NUCE) loss, which couples confidence-aware reweighting with an embedding contraction term to form compact, well-separated class clusters. NUCE consistently improves F1-score across five transformer backbones, while RF-DETR-based localization achieves state-of-the-art (SOTA) detection performance for thin, low-contrast CS structures. The source code will be made publicly available at: https://github.com/HamadYA/CS_Detection.
arXiv:2512.09461v1 Announce Type: cross
Abstract: Infertility is a major global health issue, and while in-vitro fertilization has improved treatment outcomes, embryo selection remains a critical bottleneck. Time-lapse imaging enables continuous, non-invasive monitoring of embryo development, yet most automated assessment methods rely solely on conventional morphokinetic features and overlook emerging biomarkers. Cytoplasmic Strings, thin filamentous structures connecting the inner cell mass and trophectoderm in expanded blastocysts, have been associated with faster blastocyst formation, higher blastocyst grades, and improved viability. However, CS assessment currently depends on manual visual inspection, which is labor-intensive, subjective, and severely affected by detection and subtle visual appearance. In this work, we present, to the best of our knowledge, the first computational framework for CS analysis in human IVF embryos. We first design a human-in-the-loop annotation pipeline to curate a biologically validated CS dataset from TLI videos, comprising 13,568 frames with highly sparse CS-positive instances. Building on this dataset, we propose a two-stage deep learning framework that (i) classifies CS presence at the frame level and (ii) localizes CS regions in positive cases. To address severe imbalance and feature uncertainty, we introduce the Novel Uncertainty-aware Contractive Embedding (NUCE) loss, which couples confidence-aware reweighting with an embedding contraction term to form compact, well-separated class clusters. NUCE consistently improves F1-score across five transformer backbones, while RF-DETR-based localization achieves state-of-the-art (SOTA) detection performance for thin, low-contrast CS structures. The source code will be made publicly available at: https://github.com/HamadYA/CS_Detection. Read More
Identifying Bias in Machine-generated Text Detectioncs.AI updates on arXiv.org arXiv:2512.09292v1 Announce Type: cross
Abstract: The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person. While detection models show strong performance, they have the capacity to cause significant negative impacts. We explore potential biases in English machine-generated text detection systems. We curate a dataset of student essays and assess 16 different detection systems for bias across four attributes: gender, race/ethnicity, English-language learner (ELL) status, and economic status. We evaluate these attributes using regression-based models to determine the significance and power of the effects, as well as performing subgroup analysis. We find that while biases are generally inconsistent across systems, there are several key issues: several models tend to classify disadvantaged groups as machine-generated, ELL essays are more likely to be classified as machine-generated, economically disadvantaged students’ essays are less likely to be classified as machine-generated, and non-White ELL essays are disproportionately classified as machine-generated relative to their White counterparts. Finally, we perform human annotation and find that while humans perform generally poorly at the detection task, they show no significant biases on the studied attributes.
arXiv:2512.09292v1 Announce Type: cross
Abstract: The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person. While detection models show strong performance, they have the capacity to cause significant negative impacts. We explore potential biases in English machine-generated text detection systems. We curate a dataset of student essays and assess 16 different detection systems for bias across four attributes: gender, race/ethnicity, English-language learner (ELL) status, and economic status. We evaluate these attributes using regression-based models to determine the significance and power of the effects, as well as performing subgroup analysis. We find that while biases are generally inconsistent across systems, there are several key issues: several models tend to classify disadvantaged groups as machine-generated, ELL essays are more likely to be classified as machine-generated, economically disadvantaged students’ essays are less likely to be classified as machine-generated, and non-White ELL essays are disproportionately classified as machine-generated relative to their White counterparts. Finally, we perform human annotation and find that while humans perform generally poorly at the detection task, they show no significant biases on the studied attributes. Read More
An End-to-end Planning Framework with Agentic LLMs and PDDLcs.AI updates on arXiv.org arXiv:2512.09629v1 Announce Type: new
Abstract: We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language and converts it into a PDDL (Planning Domain Definition Language) model, where the domain and problem are iteratively refined by sub-modules (agents) to address common planning requirements, such as time constraints and optimality, as well as ambiguities and contradictions that may exist in the human specification. The validated domain and problem are then passed to an external planning engine to generate a plan. The orchestrator and agents are powered by Large Language Models (LLMs) and require no human intervention at any stage of the process. Finally, a module translates the final plan back into natural language to improve human readability while maintaining the correctness of each step. We demonstrate the flexibility and effectiveness of our framework across various domains and tasks, including the Google NaturalPlan benchmark and PlanBench, as well as planning problems like Blocksworld and the Tower of Hanoi (where LLMs are known to struggle even with small instances). Our framework can be integrated with any PDDL planning engine and validator (such as Fast Downward, LPG, POPF, VAL, and uVAL, which we have tested) and represents a significant step toward end-to-end planning aided by LLMs.
arXiv:2512.09629v1 Announce Type: new
Abstract: We present an end-to-end framework for planning supported by verifiers. An orchestrator receives a human specification written in natural language and converts it into a PDDL (Planning Domain Definition Language) model, where the domain and problem are iteratively refined by sub-modules (agents) to address common planning requirements, such as time constraints and optimality, as well as ambiguities and contradictions that may exist in the human specification. The validated domain and problem are then passed to an external planning engine to generate a plan. The orchestrator and agents are powered by Large Language Models (LLMs) and require no human intervention at any stage of the process. Finally, a module translates the final plan back into natural language to improve human readability while maintaining the correctness of each step. We demonstrate the flexibility and effectiveness of our framework across various domains and tasks, including the Google NaturalPlan benchmark and PlanBench, as well as planning problems like Blocksworld and the Tower of Hanoi (where LLMs are known to struggle even with small instances). Our framework can be integrated with any PDDL planning engine and validator (such as Fast Downward, LPG, POPF, VAL, and uVAL, which we have tested) and represents a significant step toward end-to-end planning aided by LLMs. Read More
Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUscs.AI updates on arXiv.org arXiv:2503.11901v4 Announce Type: replace-cross
Abstract: This study characterizes GPU resilience in Delta, a large-scale AI system that consists of 1,056 A100 and H100 GPUs, with over 1,300 petaflops of peak throughput. We used 2.5 years of operational data (11.7 million GPU hours) on GPU errors. Our major findings include: (i) H100 GPU memory resilience is worse than A100 GPU memory, with 3.2x lower per-GPU MTBE for memory errors, (ii) The GPU memory error-recovery mechanisms on H100 GPUs are insufficient to handle the increased memory capacity, (iii) H100 GPUs demonstrate significantly improved GPU hardware resilience over A100 GPUs with respect to critical hardware components, (iv) GPU errors on both A100 and H100 GPUs frequently result in job failures due to the lack of robust recovery mechanisms at the application level, and (v) We project the impact of GPU node availability on larger-scales and find that significant overprovisioning of 5% is necessary to handle GPU failures.
arXiv:2503.11901v4 Announce Type: replace-cross
Abstract: This study characterizes GPU resilience in Delta, a large-scale AI system that consists of 1,056 A100 and H100 GPUs, with over 1,300 petaflops of peak throughput. We used 2.5 years of operational data (11.7 million GPU hours) on GPU errors. Our major findings include: (i) H100 GPU memory resilience is worse than A100 GPU memory, with 3.2x lower per-GPU MTBE for memory errors, (ii) The GPU memory error-recovery mechanisms on H100 GPUs are insufficient to handle the increased memory capacity, (iii) H100 GPUs demonstrate significantly improved GPU hardware resilience over A100 GPUs with respect to critical hardware components, (iv) GPU errors on both A100 and H100 GPUs frequently result in job failures due to the lack of robust recovery mechanisms at the application level, and (v) We project the impact of GPU node availability on larger-scales and find that significant overprovisioning of 5% is necessary to handle GPU failures. Read More