Notepad++ version 8.8.9 was released to fix a security weakness in its WinGUp update tool after researchers and users reported incidents in which the updater retrieved malicious executables instead of legitimate update packages. […] Read More
Hackers are exploiting a new, undocumented vulnerability in the implementation of the cryptographic algorithm present in Gladinet’s CentreStack and Triofox products for secure remote file access and sharing. […] Read More
An unpatched zero-day vulnerability in Gogs, a popular self-hosted Git service, has enabled attackers to gain remote code execution on Internet-facing instances and compromise hundreds of servers. […] Read More
Cybersecurity researchers have disclosed details of a new fully-featured Windows backdoor called NANOREMOTE that uses the Google Drive API for command-and-control (C2) purposes. According to a report from Elastic Security Labs, the malware shares code similarities with another implant codenamed FINALDRAFT (aka Squidoor) that employs Microsoft Graph API for C2. FINALDRAFT is attributed to a Read […]
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
Brave has introduced a new AI browsing feature that leverages Leo, its privacy-respecting AI assistant, to perform automated tasks for the user. […] 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
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
Enhanced Sentiment Interpretation via a Lexicon-Fuzzy-Transformer Frameworkcs.AI updates on arXiv.org arXiv:2510.15843v2 Announce Type: replace-cross
Abstract: Accurately detecting sentiment polarity and intensity in product reviews and social media posts remains challenging due to informal and domain-specific language. To address this, we propose a novel hybrid lexicon-fuzzy-transformer framework that combines rule-based heuristics, contextual deep learning, and fuzzy logic to generate continuous sentiment scores reflecting both polarity and strength. The pipeline begins with VADER-based initial sentiment estimations, which are refined through a two-stage adjustment process. This involves leveraging confidence scores from DistilBERT, a lightweight transformer and applying fuzzy logic principles to mitigate excessive neutrality bias and enhance granularity. A custom fuzzy inference system then maps the refined scores onto a 0 to 1 continuum, producing expert)like judgments. The framework is rigorously evaluated on four domain-specific datasets. food delivery, e-commerce, tourism, and fashion. Results show improved alignment with user ratings, better identification of sentiment extremes, and reduced misclassifications. Both quantitative metrics (distributional alignment, confusion matrices) and qualitative insights (case studies, runtime analysis) affirm the models robustness and efficiency. This work demonstrates the value of integrating symbolic reasoning with neural models for interpretable, finegrained sentiment analysis in linguistically dynamic domains.
arXiv:2510.15843v2 Announce Type: replace-cross
Abstract: Accurately detecting sentiment polarity and intensity in product reviews and social media posts remains challenging due to informal and domain-specific language. To address this, we propose a novel hybrid lexicon-fuzzy-transformer framework that combines rule-based heuristics, contextual deep learning, and fuzzy logic to generate continuous sentiment scores reflecting both polarity and strength. The pipeline begins with VADER-based initial sentiment estimations, which are refined through a two-stage adjustment process. This involves leveraging confidence scores from DistilBERT, a lightweight transformer and applying fuzzy logic principles to mitigate excessive neutrality bias and enhance granularity. A custom fuzzy inference system then maps the refined scores onto a 0 to 1 continuum, producing expert)like judgments. The framework is rigorously evaluated on four domain-specific datasets. food delivery, e-commerce, tourism, and fashion. Results show improved alignment with user ratings, better identification of sentiment extremes, and reduced misclassifications. Both quantitative metrics (distributional alignment, confusion matrices) and qualitative insights (case studies, runtime analysis) affirm the models robustness and efficiency. This work demonstrates the value of integrating symbolic reasoning with neural models for interpretable, finegrained sentiment analysis in linguistically dynamic domains. Read More
