TJS Articles & News

AutoCode: A New AI Framework that Lets LLMs Create and Verify Competitive Programming Problems, Mirroring the Workflow of Human Problem SettersMarkTechPost Are your LLM code benchmarks actually rejecting wrong-complexity solutions and interactive-protocol violations, or are they passing under-specified unit tests? A team of researchers from UCSD, NYU, University of Washington, Princeton University, Canyon Crest Academy, OpenAI, UC Berkeley, MIT, University of Waterloo, and Sentient Labs introduce AutoCode, a new AI framework that lets LLMs create and
The post AutoCode: A New AI Framework that Lets LLMs Create and Verify Competitive Programming Problems, Mirroring the Workflow of Human Problem Setters appeared first on MarkTechPost.

 Are your LLM code benchmarks actually rejecting wrong-complexity solutions and interactive-protocol violations, or are they passing under-specified unit tests? A team of researchers from UCSD, NYU, University of Washington, Princeton University, Canyon Crest Academy, OpenAI, UC Berkeley, MIT, University of Waterloo, and Sentient Labs introduce AutoCode, a new AI framework that lets LLMs create and
The post AutoCode: A New AI Framework that Lets LLMs Create and Verify Competitive Programming Problems, Mirroring the Workflow of Human Problem Setters appeared first on MarkTechPost. Read More  

Kong Releases Volcano: A TypeScript, MCP-native SDK for Building Production Ready AI Agents with LLM Reasoning and Real-World actionsMarkTechPost Kong has open-sourced Volcano, a TypeScript SDK that composes multi-step agent workflows across multiple LLM providers with native Model Context Protocol (MCP) tool use. The release coincides with broader MCP capabilities in Kong AI Gateway and Konnect, positioning Volcano as the developer SDK in an MCP-governed control plane. What Volcano provides? Volcano exposes a compact,
The post Kong Releases Volcano: A TypeScript, MCP-native SDK for Building Production Ready AI Agents with LLM Reasoning and Real-World actions appeared first on MarkTechPost.

 Kong has open-sourced Volcano, a TypeScript SDK that composes multi-step agent workflows across multiple LLM providers with native Model Context Protocol (MCP) tool use. The release coincides with broader MCP capabilities in Kong AI Gateway and Konnect, positioning Volcano as the developer SDK in an MCP-governed control plane. What Volcano provides? Volcano exposes a compact,
The post Kong Releases Volcano: A TypeScript, MCP-native SDK for Building Production Ready AI Agents with LLM Reasoning and Real-World actions appeared first on MarkTechPost. Read More  

Creating a Text to SQL App with OpenAI + FastAPI + SQLiteKDnuggets Develop a simple tool that translates natural language into queries.

 Develop a simple tool that translates natural language into queries. Read More  

A Coding Implementation to Build a Unified Tool Orchestration Framework from Documentation to Automated PipelinesMarkTechPost In this tutorial, we build a compact, efficient framework that demonstrates how to convert tool documentation into standardized, callable interfaces, register those tools in a central system, and execute them as part of an automated pipeline. As we move through each stage, we create a simple converter, design mock bioinformatics tools, organize them into a
The post A Coding Implementation to Build a Unified Tool Orchestration Framework from Documentation to Automated Pipelines appeared first on MarkTechPost.

 In this tutorial, we build a compact, efficient framework that demonstrates how to convert tool documentation into standardized, callable interfaces, register those tools in a central system, and execute them as part of an automated pipeline. As we move through each stage, we create a simple converter, design mock bioinformatics tools, organize them into a
The post A Coding Implementation to Build a Unified Tool Orchestration Framework from Documentation to Automated Pipelines appeared first on MarkTechPost. Read More  

Sigmoidal Scaling Curves Make Reinforcement Learning RL Post-Training Predictable for LLMsMarkTechPost Reinforcement Learning RL post-training is now a major lever for reasoning-centric LLMs, but unlike pre-training, it hasn’t had predictive scaling rules. Teams pour tens of thousands of GPU-hours into runs without a principled way to estimate whether a recipe will keep improving with more compute. A new research from Meta, UT Austin, UCL, Berkeley, Harvard,
The post Sigmoidal Scaling Curves Make Reinforcement Learning RL Post-Training Predictable for LLMs appeared first on MarkTechPost.

 Reinforcement Learning RL post-training is now a major lever for reasoning-centric LLMs, but unlike pre-training, it hasn’t had predictive scaling rules. Teams pour tens of thousands of GPU-hours into runs without a principled way to estimate whether a recipe will keep improving with more compute. A new research from Meta, UT Austin, UCL, Berkeley, Harvard,
The post Sigmoidal Scaling Curves Make Reinforcement Learning RL Post-Training Predictable for LLMs appeared first on MarkTechPost. Read More  

Reasoning with Sampling: Your Base Model is Smarter Than You Thinkcs.AI updates on arXiv.org arXiv:2510.14901v1 Announce Type: cross
Abstract: Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilites can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models’ own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains.

 arXiv:2510.14901v1 Announce Type: cross
Abstract: Frontier reasoning models have exhibited incredible capabilities across a wide array of disciplines, driven by posttraining large language models (LLMs) with reinforcement learning (RL). However, despite the widespread success of this paradigm, much of the literature has been devoted to disentangling truly novel behaviors that emerge during RL but are not present in the base models. In our work, we approach this question from a different angle, instead asking whether comparable reasoning capabilites can be elicited from base models at inference time by pure sampling, without any additional training. Inspired by Markov chain Monte Carlo (MCMC) techniques for sampling from sharpened distributions, we propose a simple iterative sampling algorithm leveraging the base models’ own likelihoods. Over different base models, we show that our algorithm offers substantial boosts in reasoning that nearly match and even outperform those from RL on a wide variety of single-shot tasks, including MATH500, HumanEval, and GPQA. Moreover, our sampler avoids the collapse in diversity over multiple samples that is characteristic of RL-posttraining. Crucially, our method does not require training, curated datasets, or a verifier, suggesting broad applicability beyond easily verifiable domains. Read More  

WithAnyone: Towards Controllable and ID Consistent Image Generationcs.AI updates on arXiv.org arXiv:2510.14975v1 Announce Type: cross
Abstract: Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets containing multiple images of the same individual forces most approaches to adopt reconstruction-based training. This reliance often leads to a failure mode we term copy-paste, where the model directly replicates the reference face rather than preserving identity across natural variations in pose, expression, or lighting. Such over-similarity undermines controllability and limits the expressive power of generation. To address these limitations, we (1) construct a large-scale paired dataset MultiID-2M, tailored for multi-person scenarios, providing diverse references for each identity; (2) introduce a benchmark that quantifies both copy-paste artifacts and the trade-off between identity fidelity and variation; and (3) propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity. These contributions culminate in WithAnyone, a diffusion-based model that effectively mitigates copy-paste while preserving high identity similarity. Extensive qualitative and quantitative experiments demonstrate that WithAnyone significantly reduces copy-paste artifacts, improves controllability over pose and expression, and maintains strong perceptual quality. User studies further validate that our method achieves high identity fidelity while enabling expressive controllable generation.

 arXiv:2510.14975v1 Announce Type: cross
Abstract: Identity-consistent generation has become an important focus in text-to-image research, with recent models achieving notable success in producing images aligned with a reference identity. Yet, the scarcity of large-scale paired datasets containing multiple images of the same individual forces most approaches to adopt reconstruction-based training. This reliance often leads to a failure mode we term copy-paste, where the model directly replicates the reference face rather than preserving identity across natural variations in pose, expression, or lighting. Such over-similarity undermines controllability and limits the expressive power of generation. To address these limitations, we (1) construct a large-scale paired dataset MultiID-2M, tailored for multi-person scenarios, providing diverse references for each identity; (2) introduce a benchmark that quantifies both copy-paste artifacts and the trade-off between identity fidelity and variation; and (3) propose a novel training paradigm with a contrastive identity loss that leverages paired data to balance fidelity with diversity. These contributions culminate in WithAnyone, a diffusion-based model that effectively mitigates copy-paste while preserving high identity similarity. Extensive qualitative and quantitative experiments demonstrate that WithAnyone significantly reduces copy-paste artifacts, improves controllability over pose and expression, and maintains strong perceptual quality. User studies further validate that our method achieves high identity fidelity while enabling expressive controllable generation. Read More  

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMscs.AI updates on arXiv.org arXiv:2509.13450v2 Announce Type: replace
Abstract: We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we systematically explore safety perspectives including bias, harmfulness, hallucination, social behaviors, reasoning, epistemic integrity, and normative judgment. Our framework provides modularized building blocks for state-of-the-art steering methods, enabling unified implementation of DIM, ACE, CAA, PCA, and LAT with recent enhancements like conditional steering. Results on Gemma-2-2B, Llama-3.1-8B, and Qwen-2.5-7B reveal that strong steering performance depends critically on pairing of method, model, and specific perspective. DIM shows consistent effectiveness, but all methods exhibit substantial entanglement: social behaviors show highest vulnerability (reaching degradation as high as 76%), jailbreaking often compromises normative judgment, and hallucination steering unpredictably shifts political views. Our findings underscore the critical need for holistic safety evaluations.

 arXiv:2509.13450v2 Announce Type: replace
Abstract: We introduce SteeringSafety, a systematic framework for evaluating representation steering methods across seven safety perspectives spanning 17 datasets. While prior work highlights general capabilities of representation steering, we systematically explore safety perspectives including bias, harmfulness, hallucination, social behaviors, reasoning, epistemic integrity, and normative judgment. Our framework provides modularized building blocks for state-of-the-art steering methods, enabling unified implementation of DIM, ACE, CAA, PCA, and LAT with recent enhancements like conditional steering. Results on Gemma-2-2B, Llama-3.1-8B, and Qwen-2.5-7B reveal that strong steering performance depends critically on pairing of method, model, and specific perspective. DIM shows consistent effectiveness, but all methods exhibit substantial entanglement: social behaviors show highest vulnerability (reaching degradation as high as 76%), jailbreaking often compromises normative judgment, and hallucination steering unpredictably shifts political views. Our findings underscore the critical need for holistic safety evaluations. Read More  

A Coding Guide to Build an AI-Powered Cryptographic Agent System with Hybrid Encryption, Digital Signatures, and Adaptive Security IntelligenceMarkTechPost In this tutorial, we build an AI-powered cryptographic agent system that combines the strength of classical encryption with adaptive intelligence. We design agents capable of performing hybrid encryption with RSA and AES, generating digital signatures, detecting anomalies in message patterns, and intelligently recommending key rotations. As we progress, we witness these autonomous agents securely establish
The post A Coding Guide to Build an AI-Powered Cryptographic Agent System with Hybrid Encryption, Digital Signatures, and Adaptive Security Intelligence appeared first on MarkTechPost.

 In this tutorial, we build an AI-powered cryptographic agent system that combines the strength of classical encryption with adaptive intelligence. We design agents capable of performing hybrid encryption with RSA and AES, generating digital signatures, detecting anomalies in message patterns, and intelligently recommending key rotations. As we progress, we witness these autonomous agents securely establish
The post A Coding Guide to Build an AI-Powered Cryptographic Agent System with Hybrid Encryption, Digital Signatures, and Adaptive Security Intelligence appeared first on MarkTechPost. Read More