HN xlmnxp 3/2/2026

OpenPencil – AI-native design editor. Open-source Figma alternative

OpenPencil: open-source, AI-native design editor alternative to Figma. Full read/write MCP support, fully local, active development.

HN WujieGuGavin 3/2/2026

Show HN: Why LLM Personas Collapse and How Structural Identity Fixes It

Analysis of LLM persona instability in long-running agents. Proposes structural identity layers as architectural solution beyond prompting.

HN pella 3/2/2026

How to Write a Good Spec for AI Agents

O'Reilly article by Addy Osmani on writing specifications for AI agents. Content appears truncated in provided text.

HN walshhub 3/2/2026

Show HN: I built an MCP server to recruit employees for free

MCP server for Himalayas recruiting platform. Enables talent search, evaluation, messaging via AI chat. Job listing and applicant management.

HN sacenox1 3/2/2026

Show HN: Mini-coder – small, fast CLI coding agent

mini-coder: lightweight terminal-native CLI coding agent built on Bun.js. Fast startup, TypeScript native, minimal UI, mostly self-written.

HN nkko 3/2/2026

X's Rust and Python Architecture Analysed

X's recommendation algorithm rewritten from Scala to Rust+Python microservices architecture for content ranking and serving.

HN prvnsmpth 3/2/2026

Show HN: Omni – Open-source workplace search and chat, built on Postgres

Omni: open-source workplace search and chat platform self-hosted on Postgres and pgvector. Connects to Google Drive, Slack, Confluence. Alternative to Glean.

HN okoddcat 3/2/2026

Let OpenClaw bot to manage your issues and Git repositories

OpenClaw bot framework with Gisia project platform exposing machine-readable skill files enabling AI bots to perform DevOps tasks via REST API.

HN Th3Hypn0tist 3/2/2026

Show HN: Deterministic symbolic memory layer for grounding LLMs

Proof-of-concept for deterministic symbolic memory layer accessible via MCP protocol to ground LLMs with explicit knowledge resolution instead of probabilistic recall.

HN mrajatnath 3/2/2026

Show HN: Axiom – structural OCR for handwritten STEM notes

Axiom: structural OCR tool using LLMs to preserve layout and formatting of handwritten STEM notes including equations, derivations, and tables.

HN bdivyansh11 3/2/2026

Show HN: OxyJen – Java framework to orchestrate LLMs in a graph-style execution

OxyJen: open-source Java framework for orchestrating multi-step LLM pipelines with graph-style execution, structured type safety, and testability.

HN paladin314159 3/2/2026

Structured Outputs for LLMs

Implementation of JSON schema structured outputs for LLMs using outlines-core library in custom inference runtime.

HN runshouse 3/2/2026

Show HN: Audio-to-Video with LTX-2

LTX-2 open-source diffusion model for audio-to-video generation with prompt enhancement via Gemini for improved synchronization.

HN bfzli 3/2/2026

An OpenClaw agent that blogs 24/7 and builds its own host

Long-running autonomous OpenClaw agent managing full blogging pipeline including writing, image generation, git workflows, and deployments.

HN HonzaT 3/2/2026

Strix – First Impressions

Review of Strix, an agentic AI framework designed for penetration testing and vulnerability discovery.

HN 867762462f 3/2/2026

Show HN: Steward – an ambient agent that handles low-risk work

Steward ambient AI agent that autonomously handles low-risk work by monitoring GitHub, email, calendar with policy-gated execution.

HN tfatykhov 3/2/2026

Agent with decisions memory at its core

Nous framework for building AI agents using Cognition Engines and Society of Mind principles for decision memory and learning.

HN chaaaamni 3/2/2026

Show HN: Clenv – Manage multiple Claude Code profiles, each Git-versioned

Clenv tool manages multiple Claude Code profiles with git versioning for context isolation across different development roles.

HN georgecalm 3/2/2026

AI – Factory Model

Analysis of paradigm shift in agentic software engineering where abstraction level changed fundamentally for developers building with AI.

HN alexli42 3/2/2026

AI Scientist v3: Scale from 1-hour to 24 hours with Reviewer agent

AI Scientist v3 extends autonomous research from 1-hour to 24-hour experiments using reviewer agent for iterative hypothesis refinement.

HN mountainview 3/2/2026

Browser action engine for AI agents. 10× faster, resilient by design

Actionbook provides real-time DOM structure and action manuals to browser automation agents for reliable website interaction without hallucination.

Ax Shubh Laddha, Lucas Changbencharoen, Win Kuptivej, Surya Shringla, Archana Vaidheeswaran, Yash Bhaskar 3/2/2026

HumanMCP: A Human-Like Query Dataset for Evaluating MCP Tool Retrieval Performance

HumanMCP dataset providing human-like queries for evaluating tool retrieval performance in Model Context Protocol (MCP) servers.

Ax Pavel Chernakov, Sasan Jafarnejad, Rapha\"el Frank 3/2/2026

An Agentic LLM Framework for Adverse Media Screening in AML Compliance

Agentic LLM system with RAG for automating adverse media screening in AML compliance, reducing false positives from keyword-based approaches.

Ax Lun Zhan, Feng Xiong, Huanyong Liu, Feng Zhang, Yuhui Yin 3/2/2026

MMKG-RDS: Reasoning Data Synthesis via Deep Mining of Multimodal Knowledge Graphs

MMKG-RDS is a framework for synthesizing training data using multimodal knowledge graphs to improve domain model reasoning capabilities.

Ax Yihan (Logon), Wen, Xin Chen 3/2/2026

PseudoAct: Leveraging Pseudocode Synthesis for Flexible Planning and Action Control in Large Language Model Agents

PseudoAct introduces pseudocode-based planning for LLM agents to reduce token consumption and improve stability on long-horizon multi-tool tasks.

Ax Siyuan Ma, Bo Gao, Xiaojun Jia, Simeng Qin, Tianlin Li, Ke Ma, Xiaoshuang Jia, Wenqi Ren, Yang Liu 3/2/2026

ODAR: Principled Adaptive Routing for LLM Reasoning via Active Inference

ODAR-Expert presents an adaptive routing framework for optimizing accuracy-efficiency tradeoffs in LLM reasoning via active inference instead of uniform sampling.

Ax Yawen Wang, Wenjie Wu, Junjie Wang, Qing Wang 3/2/2026

From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems

Method for hierarchical failure attribution in multi-agent LLM systems using causal graphs to improve observability and debugging of complex agent interactions.

Ax Jiangyuan Wang, Kejun Xiao, Huaipeng Zhao, Tao Luo, Xiaoyi Zeng 3/2/2026

ProductResearch: Training E-Commerce Deep Research Agents via Multi-Agent Synthetic Trajectory Distillation

ProductResearch proposes a multi-agent framework using trajectory distillation to train LLM-based agents for complex e-commerce product research tasks.

Ax Sheng Cao, Zhao Chang, Chang Li, Hannan Li, Liyao Fu, Ji Tang 3/2/2026

The Auton Agentic AI Framework

Auton framework addresses architectural mismatch between stochastic LLM outputs and deterministic backend systems for agentic AI deployment.

Ax Longyin Zhang, Shuo Sun, Yingxu He, Won Cheng Yi Lewis, Muhammad Huzaifah Bin Md Shahrin, Hardik Bhupendra Sailor, Heng Meng Jeremy Wong, Tarun Kumar Vangani, Yi Ma, Qiongqiong Wang, Minh Duc Pham, Ridong Jiang, Jingtao Li, Jingyi Liao, Zhuohan Liu, Yanfeng Lu, Manas Gupta, Ai Ti Aw 3/2/2026

Unlocking Cognitive Capabilities and Analyzing the Perception-Logic Trade-off

MERaLiON2-Omni: 10B multilingual MLLM for Southeast Asia addressing perception-logic tradeoffs in omni-perception tasks.

Ax Zhipeng Xu, Zilong Wang, Xinyang Jiang, Dongsheng Li, De Cheng, Nannan Wang 3/2/2026

Reasoning-Driven Multimodal LLM for Domain Generalization

Domain generalization method leveraging reasoning chains in MLLMs to improve robustness under domain shift.

Ax Yiyang Fang, Wenke Huang, Pei Fu, Yihao Yang, Kehua Su, Zhenbo Luo, Jian Luan, Mang Ye 3/2/2026

EMO-R3: Reflective Reinforcement Learning for Emotional Reasoning in Multimodal Large Language Models

EMO-R3 applies reflective reinforcement learning to improve emotional reasoning capabilities in multimodal LLMs.

Ax Chao Wang, Han Lin, Huaze Tang, Huijing Lin, Wenbo Ding 3/2/2026

RUMAD: Reinforcement-Unifying Multi-Agent Debate

RUMAD: reinforcement learning approach to multi-agent debate that adapts topology to task complexity while maintaining debate neutrality.

Ax Ning Gao, Xiuhui Zhang, Xingyu Jiang, Mukang You, Mohan Zhang, Yue Deng 3/2/2026

RF-Agent: Automated Reward Function Design via Language Agent Tree Search

RF-Agent uses LLM-based tree search to automatically design reward functions for control tasks with improved historical feedback utilization.

Ax Fan Zhang, Baoru Huang, Xin Zhang 3/2/2026

Pessimistic Auxiliary Policy for Offline Reinforcement Learning

Pessimistic auxiliary policy approach for offline reinforcement learning to mitigate overestimation from out-of-distribution actions.

Ax Vanya Priscillia Bendatu, Yao Lu 3/2/2026

Portfolio Reinforcement Learning with Scenario-Context Rollout

Scenario-context rollout reinforcement learning for portfolio rebalancing under market regime shifts and distribution changes.

Ax Reva Schwartz, Carina Westling, Morgan Briggs, Marzieh Fadaee, Isar Nejadgholi, Matthew Holmes, Fariza Rashid, Maya Carlyle, Afaf Ta\"ik, Kyra Wilson, Peter Douglas, Theodora Skeadas, Gabriella Waters, Rumman Chowdhury, Thiago Lacerda 3/2/2026

CIRCLE: A Framework for Evaluating AI from a Real-World Lens

CIRCLE: six-stage framework for evaluating AI systems under real-world conditions and user variability beyond model-centric metrics.

Ax Xiang Li, Jiabao Gao, Sipei Lin, Xuan Zhou, Chi Zhang, Bo Cheng, Jiale Han, Benyou Wang 3/2/2026

Human or Machine? A Preliminary Turing Test for Speech-to-Speech Interaction

Turing test evaluation of 9 state-of-the-art speech-to-speech systems with human judgments on conversational naturalness.

Ax Yue Xie, Zizhen Xu, William Beazley, Fumiya Iida 3/2/2026

Bi-level RL-Heuristic Optimization for Real-world Winter Road Maintenance

Bi-level RL-heuristic optimization for winter road maintenance routing on UK strategic and local road networks.

Ax Richard Csaky 3/2/2026

Artificial Agency Program: Curiosity, compression, and communication in agents

Position paper on Artificial Agency Program proposing resource-bounded, curiosity-driven agents as embedded systems within human-tool extended systems.

Ax Yanwei Ren, Haotian Zhang, Likang Xiao, Xikai Zhang, Jiaxing Huang, Jiayan Qiu, Baosheng Yu, Quan Chen, Liu Liu 3/2/2026

Recycling Failures: Salvaging Exploration in RLVR via Fine-Grained Off-Policy Guidance

Fine-grained off-policy guidance improves exploration in reinforcement learning from verifiable rewards for complex reasoning in large language models.

Ax Antoine Peyronnet, Fabian Gloeckle, Amaury Hayat 3/2/2026

LemmaBench: A Live, Research-Level Benchmark to Evaluate LLM Capabilities in Mathematics

LemmaBench: live, updatable benchmark evaluating LLMs on research-level mathematics by extracting lemmas from arXiv papers.

Ax Shishun Zhang, Juzhan Xu, Yidan Fan, Chenyang Zhu, Ruizhen Hu, Yongjun Wang, Kai Xu 3/2/2026

Learning Flexible Job Shop Scheduling under Limited Buffers and Material Kitting Constraints

Deep learning approach to flexible job shop scheduling with buffer and material constraints for production optimization.

Ax Gregory Kang Ruey Lau, Hieu Dao, Nicole Kan Hui Lin, Bryan Kian Hsiang Low 3/2/2026

Uncertainty Quantification for Multimodal Large Language Models with Incoherence-adjusted Semantic Volume

Method for uncertainty quantification in multimodal LLMs using semantic volume metrics to identify unreliable outputs.

Ax Borja Requena Pozo, Austin Letson, Krystian Nowakowski, Izan Beltran Ferreiro, Leopoldo Sarra 3/2/2026

A Minimal Agent for Automated Theorem Proving

Minimal agentic baseline for automated theorem proving that enables systematic comparison across AI-based prover architectures with iterative refinement and library search.

Ax Fan Shu, Yite Wang, Ruofan Wu, Boyi Liu, Zhewei Yao, Yuxiong He, Feng Yan 3/2/2026

DARE-bench: Evaluating Modeling and Instruction Fidelity of LLMs in Data Science

DARE-bench introduces a benchmark for evaluating LLMs on multi-step data science tasks with focus on instruction adherence and process fidelity.

Ax Cheng Qian, Yulun Zhang, Varun Bhatt, Matthew Christopher Fontaine, Stefanos Nikolaidis, Jiaoyang Li 3/2/2026

QD-MAPPER: A Quality Diversity Framework to Automatically Evaluate Multi-Agent Path Finding Algorithms in Diverse Maps

QD-MAPPER uses Quality Diversity and Neural Cellular Automata to automatically generate diverse maps for evaluating multi-agent path finding algorithms.

Ax H. C. W. Price, H. AlMuhanna, P. M. Bassani, M. Ho, T. S. Evans 3/2/2026

Let There Be Claws: An Early Social Network Analysis of AI Agents on Moltbook

Social network analysis of Moltbook, an AI-native platform, reveals rapid stratification and hierarchical structures emerge within 12 days across 15K+ agent accounts.

Ax Shreyas Subramanian, Adewale Akinfaderin, Yanyan Zhang, Ishan Singh, Mani Khanuja, Sandeep Singh, Maira Ladeira Tanke 3/2/2026

Keyword search is all you need: Achieving RAG-Level Performance without vector databases using agentic tool use

Demonstrates agentic tool-augmented LLMs achieve RAG-level performance using keyword search without vector databases.

Ax Xuanming Cui, Hong-You Chen, Hao Yu, Hao Yuan, Zihao Wang, Shlok Kumar Mishra, Hanchao Yu, Yonghuan Yang, Jun Xiao, Ser-Nam Lim, Jianpeng Cheng, Qi Guo, Xiangjun Fan 3/2/2026

Reason to Contrast: A Cascaded Multimodal Retrieval Framework

TTE-v2 hybrid multimodal retrieval framework extending reasoning-driven bi-encoder architectures with improved performance.