HN mvdwoord 3/11/2026

A static recompiler for original GameBoy ROMs

Static recompiler translating original GameBoy Z80 assembly into portable C code.

HN joozio 3/11/2026

The Download: AI's role in the Iran war, and an escalating legal fight

News article on AI's role in Iran conflict and military decision-making systems.

LB jnsgr.uk via knx 3/11/2026

Brewlog: Coffee & Agents

Personal blog about tracking coffee habits with an iOS app and building a custom data system.

HN cashmere1337 3/11/2026

Show HN: kitty-graphics.el – Images, LaTeX and PDFs in terminal Emacs

Emacs extension using Kitty graphics protocol to display images in terminal mode via Claude API.

HN frozenseven 3/11/2026

AutoKernel: Autoresearch for GPU Kernels

AutoKernel uses AI agents to autonomously optimize PyTorch models into Triton GPU kernels via iterative testing and refinement.

HN ashmil 3/11/2026

I Reduced 5 hours of Testing my Agentic AI applcaition to 10 mins

LLMSec framework for testing and evaluating agentic AI applications with autonomous security testing and attack simulation.

HN JeanKage 3/11/2026

Microsoft patents system for AI helpers to finish games for you

Microsoft patents AI system to automatically complete game sections for players.

HN bohdokas 3/11/2026

PromptVault free tool for multi agentic development

PromptVault desktop app for versioning prompts in multi-agent pipelines, logging outputs, and tracking agent configurations locally.

HN Barathkanna 3/11/2026

Ask HN: How are people forecasting AI API costs for agent workflows?

HN discussion on forecasting and managing API costs for LLM-based agent workflows in production.

HN smusamashah 3/11/2026

TADA: Fast, Reliable Speech Generation Through Text-Acoustic Synchronization

TADA: Novel text-acoustic tokenization schema for faster, more reliable LLM-based text-to-speech synthesis.

HN softcane 3/11/2026

Show HN: Self-hosted DCF workspace using Damodaran datasets, LLM narratives

Self-hosted DCF valuation tool using LLM narratives and Damodaran datasets with transparent assumptions.

HN weltview 3/11/2026

OWASP Top Agents and AI Vulnerabilities

OWASP analysis of security vulnerabilities specific to AI agents: non-determinism, mixed instruction/data, and API access risks.

HN ArmaloAI 3/11/2026

We built NPM for agent knowledge – Context Packs on Armalo (update)

Armalo Context Packs: NPM-like package manager for agent knowledge with trust and commerce layers for multi-agent systems.

HN 1vuio0pswjnm7 3/11/2026

Why Ads in Chatbots May Not Click

Brief headline on advertising effectiveness in chatbots.

HN rusanovych 3/11/2026

Neuromorphic sphere topology Hebbian learning as a path to grounded intelligence

Hypothesis discussion on intelligence as phase transition at scale requiring grounding rather than architecture alone.

HN anthony-maio 3/11/2026

Mnemos – scoped local memory for coding agents (public beta)

Mnemos: Scoped memory system for coding agents with project/workspace/global separation, MCP integration, adaptive retrieval.

HN mattcameron 3/11/2026

Are You Comfortable Putting Your Name on This? (AI-Assisted Development)

Discussion on responsibility and human judgment in shipping AI-assisted code; emphasis on quality over speed.

HN anil789 3/11/2026

We Built a 100K-Line Enterprise App Using AI – Here's Why Vibe-Coding Couldn't

Case study: Generated 100K-line enterprise aircraft MRO app in one week using AI, 50-60% of production code.

HN shashahchk 3/11/2026

Are you letting agents run infra tools / scripts yet?

HN discussion on using AI agents for infrastructure operations: migrations, deployments, provisioning, and MCP servers.

HN ketanbj 3/11/2026

Separating AI agent reasoning from execution, crypto binding execution

Discussion on separating AI agent reasoning from execution with cryptographic binding.

HN surprisetalk 3/11/2026

Improving instruction hierarchy in frontier LLMs

IH-Challenge: training dataset and research improving instruction hierarchy, safety steerability, and prompt injection robustness in frontier LLMs.

HN EmptyDrum 3/11/2026

Maybe we can keep on coding? pseudo code project

Pseudo-Code-Flow: Claude-based tool enabling developers to write pseudocode and automatically translate to real code, leveraging LLM translation capabilities.

Ax Cornelius Emde, Alexander Rubinstein, Anmol Goel, Ahmed Heakl, Sangdoo Yun, Seong Joon Oh, Martin Gubri 3/11/2026

MASEval: Extending Multi-Agent Evaluation from Models to Systems

MASEval: benchmark extending multi-agent evaluation beyond models to system components, comparing topologies, orchestration logic, and error handling across LLM frameworks.

Ax Sunil Prakash 3/11/2026

LDP: An Identity-Aware Protocol for Multi-Agent LLM Systems

LDP: AI-native communication protocol for multi-agent LLM systems exposing model identity, reasoning profile, quality calibration, and cost as first-class primitives.

Ax Kyle McCleary, James Ghawaly 3/11/2026

Quantifying the Accuracy and Cost Impact of Design Decisions in Budget-Constrained Agentic LLM Search

BCAS: controlled measurement study quantifying how search depth, retrieval strategy, and token budget affect accuracy and cost in agentic RAG systems.

Ax Joshua Castillo, Ravi Mukkamala 3/11/2026

Interpretable Markov-Based Spatiotemporal Risk Surfaces for Missing-Child Search Planning with Reinforcement Learning and LLM-Based Quality Assurance

Guardian system combining reinforcement learning with LLM-based QA to generate interpretable spatiotemporal risk surfaces for missing-child search planning from unstructured case data.

Ax Rui Liu, Tao Zhe, Dongjie Wang, Zijun Yao, Kunpeng Liu, Yanjie Fu, Huan Liu, Jian Pei 3/11/2026

AgentOS: From Application Silos to a Natural Language-Driven Data Ecosystem

AgentOS: operating system architecture enabling locally-hosted LLM agents to autonomously operate computing environments, orchestrate workflows, and integrate external tools.

Ax Joshua Castillo, Ravi Mukkamala 3/11/2026

A Consensus-Driven Multi-LLM Pipeline for Missing-Person Investigations

Guardian: multi-LLM pipeline system for missing-person investigations using consensus-driven LLM coordination for intelligent information extraction and search planning.

Ax I. Samuel Akinwande, Sydney M. Katz, Mykel J. Kochenderfer, Clark Barrett 3/11/2026

The FABRIC Strategy for Verifying Neural Feedback Systems

FABRIC strategy for backward reachability analysis and verification of neural feedback systems controlled by neural networks.

Ax Yixiong Chen, Xinyi Bai, Yue Pan, Zongwei Zhou, Alan Yuille 3/11/2026

Meissa: Multi-modal Medical Agentic Intelligence

Meissa: open-source multi-modal medical agentic system combining medical image understanding with tool use and multi-agent collaboration, deployable on-premise without frontier models.

Ax Yunfei Xie, Kevin Wang, Bobby Cheng, Jianzhu Yao, Zhizhou Sha, Alexander Duffy, Yihan Xi, Hongyuan Mei, Cheston Tan, Chen Wei, Pramod Viswanath, Zhangyang Wang 3/11/2026

MEMO: Memory-Augmented Model Context Optimization for Robust Multi-Turn Multi-Agent LLM Games

MEMO: memory-augmented optimization reducing run-to-run variance in multi-turn multi-agent LLM games by stabilizing prompt policies and improving ranking reliability.

Ax Elija Perrier, Michael Timothy Bennett 3/11/2026

Time, Identity and Consciousness in Language Model Agents

Philosophical analysis of temporal coherence and consciousness evaluation in LLM agents, examining whether agents' self-descriptions match actual decision constraints.

Ax Zhanlin Liu, Yitao Li, Munirathnam Srikanth 3/11/2026

EPOCH: An Agentic Protocol for Multi-Round System Optimization

EPOCH: engineering protocol for autonomous agents to perform iterative multi-round optimization of prompts, code, and ML systems in heterogeneous environments.

Ax Seunghwan Kim (AnsibleHealth Inc., San Francisco, USA), Tiffany H. Kung (AnsibleHealth Inc., San Francisco, USA, Stanford School of Medicine, Stanford, USA), Heena Verma (AnsibleHealth Inc., San Francisco, USA), Dilan Edirisinghe (AnsibleHealth Inc., San Francisco, USA), Kaveh Sedehi (AnsibleHealth Inc., San Francisco, USA), Johanna Alvarez (AnsibleHealth Inc., San Francisco, USA), Diane Shilling (AnsibleHealth Inc., San Francisco, USA), Audra Lisa Doyle (AnsibleHealth Inc., San Francisco, USA), Ajit Chary (AnsibleHealth Inc., San Francisco, USA), William Borden (AnsibleHealth Inc., San Francisco, USA, George Washington University, Washington, D.C., USA), Ming Jack Po (AnsibleHealth Inc., San Francisco, USA) 3/11/2026

From Days to Minutes: An Autonomous AI Agent Achieves Reliable Clinical Triage in Remote Patient Monitoring

Sentinel: autonomous AI agent for remote patient monitoring clinical triage using Model Context Protocol and 21 clinical tools, reducing manual review from days to minutes.

Ax Hajime Shimao, Warut Khern-am-nuai, Sung Joo Kim 3/11/2026

Chaotic Dynamics in Multi-LLM Deliberation

Research on stability and chaotic dynamics in multi-LLM committee systems using Lyapunov exponents to measure inter-run sensitivity across policy scenarios.

Ax Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Siyu An, Di Yin, Xing Sun, Feiyue Huang 3/11/2026

Deep Tabular Research via Continual Experience-Driven Execution

Deep Tabular Research agentic framework for multi-step reasoning over complex hierarchical tables using closed-loop decision-making.

Ax Tong Wang, Chi Jin, Yongkang Chen, Huan Deng, Xiaohui Kuang, Gang Zhao 3/11/2026

DataFactory: Collaborative Multi-Agent Framework for Advanced Table Question Answering

DataFactory multi-agent framework for table question answering, addressing context constraints, hallucination, and complex reasoning over structured data.

Ax Tavishi Sharma, Vinayak Sharma, Pragya Sharma 3/11/2026

Real-Time Trust Verification for Safe Agentic Actions using TrustBench

TrustBench framework for real-time action verification in autonomous agents, preventing harmful actions during execution rather than post-hoc evaluation.

Ax Renwei Meng 3/11/2026

Explainable Innovation Engine: Dual-Tree Agent-RAG with Methods-as-Nodes and Verifiable Write-Back

Explainable Innovation Engine upgrades RAG with methods-as-nodes, weighted provenance trees, and hierarchical clustering for traceable multi-step synthesis.

Ax Subramanyam Sahoo, Aman Chadha, Vinija Jain, Divya Chaudhary 3/11/2026

The Reasoning Trap -- Logical Reasoning as a Mechanistic Pathway to Situational Awareness

Research on logical reasoning as mechanistic pathway to situational awareness in LLMs, examining risks of advanced reasoning capabilities.

Ax Jiangming Shu, Yuxiang Zhang, Ye Ma, Xueyuan Lin, Jitao Sang 3/11/2026

Evaluate-as-Action: Self-Evaluated Process Rewards for Retrieval-Augmented Agents

EvalAct framework converts implicit retrieval quality assessment into explicit action for improving multi-step reasoning in retrieval-augmented agents.

Ax Xupeng Chen 3/11/2026

Abundant Intelligence and Deficient Demand: A Macro-Financial Stress Test of Rapid AI Adoption

Macro-financial analysis of rapid AI adoption examining economic distribution mismatch and institutional anchoring to human cognitive scarcity.

Ax Bhanuka Silva, Dishanika Denipitiyage, Anirban Mahanti, Aruna Seneviratne, Suranga Seneviratne 3/11/2026

PrivPRISM: Automatically Detecting Discrepancies Between Google Play Data Safety Declarations and Developer Privacy Policies

PrivPRISM framework detecting discrepancies between Google Play data safety declarations and developer privacy policies using language models.

Ax Ding Linghu, Cheng Wang, Da Fan, Wei Shi, Kaifeng Yin, Xiaoliang Xue, Fan Yang, Haiyi Ren, Cong Zhang 3/11/2026

Cognitively Layered Data Synthesis for Domain Adaptation of LLMs to Space Situational Awareness

Data synthesis approach for domain-adapting LLMs to space situational awareness through cognitively layered supervision and engineering specifications.

Ax Jincenzi Wu, Yuxuan Lei, Jianxun Lian, Yitian Huang, Lexin Zhou, Haotian Li, Xing Xie, Helen Meng 3/11/2026

Social-R1: Towards Human-like Social Reasoning in LLMs

Social-R1 framework enhancing social reasoning in LLMs for perceiving social cues and inferring mental states in human-AI collaboration.

Ax Haibin Wen, Zhe Zhao, Fanfu Wang, Tianyi Xu, Hao Zhang, Chao Yang, Ye Wei 3/11/2026

Logos: An evolvable reasoning engine for rational molecular design

Logos reasoning engine for molecular design combining machine learning predictions with transparent chemical reasoning and validity guarantees.

Ax Yuyang Dai 3/11/2026

Rescaling Confidence: What Scale Design Reveals About LLM Metacognition

Study of verbalized confidence scales in LLMs, showing heavy discretization around round numbers and implications for uncertainty estimation.

Ax Shivam Raval, Hae Jin Song, Linlin Wu, Abir Harrasse, Jeff Phillips, Amirali Abdullah 3/11/2026

Curveball Steering: The Right Direction To Steer Isn't Always Linear

Analysis of nonlinear activation steering in LLMs, questioning linear representation hypothesis and demonstrating inconsistent behavior of linear interventions.

Ax Hongqiang Lin, Zhenghui Fu, Weihao Tang, Pengfei Wang, Yiding Sun, Qixian Huang, Dongxu Zhang 3/11/2026

Robust Regularized Policy Iteration under Transition Uncertainty

Offline reinforcement learning approach using robust policy optimization to handle distribution shift and transition uncertainty.

Ax Athanasios Davvetas, Michael Papademas, Xenia Ziouvelou, Vangelis Karkaletsis 3/11/2026

AI Act Evaluation Benchmark: An Open, Transparent, and Reproducible Evaluation Dataset for NLP and RAG Systems

Open evaluation benchmark for assessing NLP and RAG systems' compliance with EU AI Act regulatory standards.