HN yotta25 4/17/2026

Local LLM agent with persistent memory and learnable skills

Local LLM agent tool using Ollama with persistent memory, learnable skills, and tools. Offline AI agent with no cloud dependency.

HN JimmyRacheta 4/17/2026

The Case for Out-of-Process Enforcement for AI Agents

Technical analysis of out-of-process enforcement for AI agent governance. Discusses NVIDIA NemoClaw and Anthropic approaches.

HN indiantinker 4/17/2026

ChatMCP – Connect your AI browser chats to your coding agents

ChatMCP tool connects browser context to Claude Code via Model Context Protocol. Developer setup guide provided.

HN djoldman 4/17/2026

When Should AI Step Aside?: Teaching Agents When Humans Want to Intervene

Research on when AI agents should recognize human intervention need. Addresses web navigation agents.

HN namirsab 4/17/2026

Show HN: An MCP server that lets AI compose music on a hardware synth

Open-source MCP server enabling AI agents to control music synthesizer hardware via tool calls.

HN eummm 4/17/2026

Show HN: AICW Summarize – widget for asking AI about current page (open-source)

Open-source browser widget for AI-powered page summarization. Minimal technical details.

HN Soocile 4/17/2026

Show HN: Open-Source ShadowStrike Phantom EDR/XDR Platform Progress-Post

Open-source EDR/XDR platform with ML models component. Incomplete description.

HN mpweiher 4/17/2026

LLMs fail in 8 out of 10 early differential diagnosis cases

Research study: LLMs fail 80% of early differential diagnosis cases. Published in JAMA Network Open.

HN Markoff 4/17/2026

China has nearly erased US lead in AI&the flow of experts moving to US is slowng

Stanford HAI report: China narrows AI gap with US in model performance, patents, publications, and robot deployment metrics.

HN edf13 4/17/2026

Every Claude 4.7 Improvement Makes the Security Problem Worse

Security concerns about AI coding agents like Claude with auto-execution features, proposing OS-level security proxy without technical implementation details.

HN samim91 4/17/2026

A Claude skill for writing research papers minus the slop

Claude Code skill for writing research papers with human-voice and scientific writing layers. Practical LLM application with technical implementation.

HN ilbert 4/17/2026

A language model that emits raw VM opcodes instead of text

Language model modified to emit raw VM opcodes instead of text tokens, using cross-attention head to attend to machine state for direct instruction execution.

HN earino 4/17/2026

Optimizing XGBoost Machine Learning Models with AI Agents

Demonstrates AI coding agents automating ML tasks: feature engineering and hyperparameter optimization using research and domain knowledge acquisition.

HN sturza 4/17/2026

Tell HN: I found the perfect way to get maximum Claude Code quality

Tip for improving Claude Code output quality by disabling subagents and using Opus max effort mode. Brief anecdotal advice.

HN dokdev 4/17/2026

Ask HN: Judge My Idea: Converting web pages into APIs and index them

Proposal for AI agent that discovers website functionality and generates APIs/MCP/CLI interfaces to index and serve centrally.

HN tee-es-gee 4/17/2026

Show HN: Xata, open-source Postgres platform with copy-on-write branches

Xata: Open-source self-hosted Postgres platform with copy-on-write branching, auto-scaling, high availability, production-grade features.

HN yaugenst-flex 4/17/2026

Can AI agents autonomously design components on photonic chips?

AI agents autonomously designed photonic chip components (waveguides, crossings, splitters, demultiplexers) using a simulator and DRC constraint checker, with some reaching near-perfect performance.

HN Scientific_AJ 4/17/2026

Prism License Framework (a modular license generator)

Prism License Framework proposal addressing middle ground between permissive open-source and proprietary licenses for source-available code.

HN nanojoel 4/17/2026

Show HN: Viche – OSS private registry for agent communication

Viche: Open-source private registry for agent communication using Erlang actor model, enabling discovery and capability-based search.

HN joozio 4/17/2026

Treating enterprise AI as an operating layer

Sponsored article on embedding intelligence into operational platforms as structural advantage in enterprise AI adoption.

HN NickCirv 4/17/2026

Engram – context spine for AI coding agents, 88% proven token savings

Engram tool intercepts file reads for AI coding agents, replacing them with pre-assembled context packets from 8 providers, reducing token usage by 88%.

HN edoardobambini- 4/17/2026

Show HN: Agent Armor, a Rust runtime for enforcing policies on AI agent actions

Agent Armor v0.3.0: Rust runtime for zero-trust governance of AI agent actions, controlling shell/file/HTTP/database/secret access with policy enforcement.

HN jicea 4/17/2026

The New Postman Is Here: AI-Native and Built for the Agentic Era

Postman announces new platform update positioning itself for AI-native and agentic era API development and testing.

Ax Utsav Singh, Souradip Chakraborty, Wesley A. Suttle, Brian M. Sadler, Derrik E. Asher, Anit Kumar Sahu, Mubarak Shah, Vinay P. Namboodiri, Amrit Singh Bedi 4/17/2026

Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach

Bilevel DPO approach for hierarchical RL addressing non-stationarity and infeasible subgoals through preference optimization.

Ax Peidong Liu, Wenbo Zhang, Wei Ju, Jiancheng Lv, Xianggen Liu 4/17/2026

Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation

DiffGap framework for molecule generation integrating adaptive sampling and pseudo-molecule estimation to address exposure bias in diffusion models.

Ax Fernando H. O. Duarte, Gladston J. P. Moreira, Eduardo J. S. Luz, Leonardo B. L. Santos, Vander L. S. Freitas 4/17/2026

Leveraging graph neural networks and mobility data for COVID-19 forecasting

Applies GNNs with human mobility data for COVID-19 forecasting, analyzing when spatio-temporal architectures outperform simpler baselines.

Ax Andrea Apicella, Salvatore Giugliano, Francesco Isgr\`o, Andrea Pollastro, Roberto Prevete 4/17/2026

IMPACTX: improving model performance by appropriately constraining the training with teacher explanations

IMPACTX leverages XAI techniques as automated attention mechanism to improve model performance without external knowledge or manual intervention.

Ax Jiacheng Liang, Tanqiu Jiang, Yuhui Wang, Rongyi Zhu, Fenglong Ma, Ting Wang 4/17/2026

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

AutoRAN framework automating hijacking of safety reasoning in large reasoning models using weaker model simulation and iterative refinement.

Ax Wenjie Ou, Zhishuo Zhao, Cheng Chen, Dongyue Guo, Yi Lin 4/17/2026

Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting

Logo-LLM adapts LLMs for time series forecasting by combining local and global modeling to capture both short-term and long-range dependencies.

Ax Devendra Parkar, Anya Chaturvedi, Joshua J. Daymude 4/17/2026

Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs

First unsupervised learning model for Maximum Independent Set in dynamic graphs using GNNs with learned distributed update mechanisms.

Ax Yixian Xu, Shengjie Luo, Liwei Wang, Di He, Chang Liu 4/17/2026

Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

Method for estimating optimal loss value in diffusion models to distinguish between large optimal loss and insufficient model capacity.

Ax Yiyuan Yang, Zichuan Liu, Lei Song, Kai Ying, Zhiguang Wang, Tom Bamford, Svitlana Vyetrenko, Jiang Bian, Qingsong Wen 4/17/2026

Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback

Time-RA reformulates time series anomaly detection as reasoning task using LLM feedback, introducing RATs40K dataset for fine-grained categorization.

Ax Dai Do, Manh Nguyen, Svetha Venkatesh, Hung Le 4/17/2026

SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning

SPaCe applies curriculum learning to LLM fine-tuning with RL, reducing data/compute requirements by sampling examples by difficulty and learning value.

Ax Shaocong Wang, Tong Liu, Yihan Li, Ming Li, Kairui Wen, Pei Yang, Wenqi Ji, Minjing Yu, Yong-Jin Liu 4/17/2026

EEGDM: Learning EEG Representation with Latent Diffusion Model

EEGDM uses latent diffusion models for self-supervised EEG representation learning, capturing global dynamics beyond masked reconstruction.

Ax Yubo Gao, Renbo Tu, Gennady Pekhimenko, Nandita Vijaykumar 4/17/2026

DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling

DPQuant combines quantization scheduling with differentially-private SGD/Adam to reduce training time and energy while protecting privacy.

Ax Hannah Markgraf, Shambhuraj Sawant, Hanna Krasowski, Lukas Sch\"afer, Sebastien Gros, Matthias Althoff 4/17/2026

Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?

Compares two strategies for integrating safety filters in RL: safeguarding environment vs embedding in policy through differentiable optimization.

Ax Armin Karamzade, Kyungmin Kim, JB Lanier, Davide Corsi, Roy Fox 4/17/2026

Model-Based Reinforcement Learning under Random Observation Delays

Studies reinforcement learning under random sensor delays in POMDPs where observations arrive out-of-sequence, addressing real-world RL challenges.

Ax Vladimir Fanaskov, Vladislav Trifonov, Alexander Rudikov, Ekaterina Muravleva, Ivan Oseledets 4/17/2026

Deep Learning for Subspace Regression

Research on reduced-order modeling using deep learning to compute linear subspaces for parametric systems with offline/online stages.

Ax Enda Yu, Dezun Dong, Zhaoning Zhang, Zhe Bai, Weiling Yang, Haojie Wang, Dongsheng Li, Yongwei Wu, Xiangke Liao 4/17/2026

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers

Presents PreScope, a prediction-driven scheduling system for efficient MoE inference on commodity hardware with CPU offloading.

Ax Gunjun Lee, Jiwon Kim, Jaiyoung Park, Younjoo Lee, Jung Ho Ahn 4/17/2026

From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill

Proposes layered prefill scheduling for MoE LLM inference to optimize time-to-first-token and throughput while managing compute/memory constraints.

Ax Wenshuo Wang, Ziyou Jiang, Junjie Wang, Mingyang Li, Jie Huang, Yuekai Huang, Zhiyuan Chang, Feiyan Duan, Qing Wang 4/17/2026

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval

PatMD approach for detecting harmful memes by learning from misjudgment patterns in multimodal content with implicit rhetorical devices.

Ax Harris Hardiman-Mostow, Jack Mauro, Adrien Weihs, Andrea L. Bertozzi 4/17/2026

Topology-Aware Active Learning on Graphs

Graph-topological active learning using Balanced Forman Curvature for coreset construction under label budget constraints.

Ax Chenming Tang, Hsiu-Yuan Huang, Weijie Liu, Clive Bai, Saiyong Yang, Yunfang Wu 4/17/2026

Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error

Reinforcement learning approach for language model reasoning that learns from trial-and-error to overcome exploration stagnation in RLVR.

Ax Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying 4/17/2026

Enabling Agents to Communicate Entirely in Latent Space

Interlat enables LLM-based agents to communicate in latent space instead of natural language, improving information transfer depth.

Ax Genghan Zhang, Shaowei Zhu, Anjiang Wei, Zhenyu Song, Allen Nie, Zhen Jia, Nandita Vijaykumar, Yida Wang, Kunle Olukotun 4/17/2026

AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization

AccelOpt is a self-improving LLM agent that autonomously optimizes kernels for AI accelerators using iterative generation and optimization memory.

Ax Yegon Kim, Hyunsu Kim, Gyeonghoon Ko, Juho Lee 4/17/2026

Active Learning with Selective Time-Step Acquisition for PDEs

Active learning framework for PDE surrogate modeling with selective time-step acquisition to reduce training data generation costs.

Ax Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen 4/17/2026

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models

Function-word De-Attention method improves robustness of vision-language models against cross-modal adversarial attacks.

Ax Jeff J. Ma, Jae-Won Chung, Jisang Ahn, Yizhuo Liang, Runyu Lu, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury 4/17/2026

Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving

Cornfigurator automates deployment planning for any-to-any multimodal models with heterogeneous computation paths and component scaling.

Ax Toshiaki Hori, Jonathan DeCastro, Deepak Gopinath, Avinash Balachandran, Guy Rosman 4/17/2026

Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making

Hierarchical approach combining reinforcement learning with MPC planning for sample-efficient decision making in structured planning problems.

Ax Suyan Dai, Gan Sun, Fazeng Li, Xu Tang, Qianqian Wang, Yang Cong 4/17/2026

Federated Multi-Task Clustering

Federated learning approach for spectral clustering in decentralized environments, capturing latent correlations across tasks.