2/27/2026
Show HN: AgentWeb – Free business directory API for AI agents (11M+ businesses)
Free business directory API with 11M+ businesses, full-text search and geo-location for AI agents to query real-world business data reliably.
2/27/2026
Governing Autonomous AI Agents in Production
Framework for governing autonomous AI agents in production environments, addressing safety and control.
2/27/2026
LLMs Generate Predictable Passwords
Research on LLM-generated passwords being predictable, exposing security vulnerabilities in password generation tasks.
2/27/2026
Ask HN: Have LLMs sapped your motivation for open source?
Discussion about how LLM prevalence affects open source contributor motivation and reputation, questioning whether AI-generated code diminishes accomplishment recognition.
2/27/2026
Claude Code Skills and 380 agent skills from official dev teams and community
Collection of 380+ agent skills from Anthropic, Google, Vercel, Stripe and other teams for use with Claude, Codex, Gemini CLI and similar platforms. Real-world skills, not auto-generated.
2/27/2026
AI agents are fast, loose, and out of control, MIT study finds (ZDNET)
MIT study reports agentic AI moving mainstream with capabilities outpacing governance; notes OpenAI hired OpenClaw framework creator.
2/27/2026
AI Agent Crypto Wallets Create New Legal Risks, Investors Warn
Analysis of legal and regulatory risks from AI agents equipped with crypto wallets for autonomous transactions and hiring.
2/27/2026
Get free Claude max 20x for open-source maintainers
Anthropic offers 6 months free Claude Max 20x to open-source maintainers and contributors through rolling application review.
2/27/2026
Show HN: RunVeto – A Simple Kill Switch for Autonomous AI Agents
Kill switch governance tool for autonomous AI agents using LangChain, preventing agent sprawl and cost overruns from runaway recursion.
2/27/2026
The LLM App Isn't a Model, It's a System: Designing for Quarterly Model Swaps
Discusses designing LLM applications as systems built around models, planning for quarterly model swaps rather than model-centric architecture.
2/27/2026
HikmaAI – The AI Agent Supply Chain is Broken. Here is how we fix it
Claim that AI agent supply chain has problems with proposed solutions, no substantive details provided.
2/27/2026
AI voice agents for hotels: lessons from 15,910 real guest calls
Case study of AI voice agents deployed in hotels analyzing 15,910 real guest interactions and lessons learned from deployment.
2/27/2026
AI Assisted Coding
Personal experience using AI-assisted coding with GLM 4.7/5 models and Claude CLI for debugging and development tasks, particularly Vulkan code.
2/27/2026
Show HN: Docsome – Single Markdown file to featured static documentation
Open source static documentation generator from single Markdown file with AI agent support via llms.txt format. Includes CLI tool, dark mode, search indexing.
2/27/2026
OpenAI and Amazon announce strategic partnership
OpenAI and Amazon announce multi-year strategic partnership with $50B investment. Joint development of Stateful Runtime Environment for enterprise AI.
2/27/2026
Introducing the Stateful Runtime Environment for Agents in Amazon Bedrock
Amazon Bedrock launches Stateful Runtime Environment for AI agents, powered by OpenAI models. Enables multi-step reliable agent execution with tool integration and operational controls.
2/27/2026
Takeuchi's Information Criteria as Generalization Measures for DNNs Close to NTK Regime
Theoretical study of Takeuchi's information criterion as a generalization measure for deep neural networks in the neural tangent kernel regime.
2/27/2026
Physics Informed Viscous Value Representations
Offline reinforcement learning approach using physics-informed constraints via PDEs to improve value function estimation in goal-conditioned policies.
2/27/2026
ParamMem: Augmenting Language Agents with Parametric Reflective Memory
ParamMem augments language agents with parametric reflective memory to improve reasoning by increasing reflection diversity.
2/27/2026
Differentiable Zero-One Loss via Hypersimplex Projections
Differentiable approximation to zero-one loss via hypersimplex projections for end-to-end optimizable classification models.
2/27/2026
FlashOptim: Optimizers for Memory Efficient Training
Memory-efficient optimizer suite (FlashOptim) for training large language models with reduced accelerator memory requirements.
2/27/2026
SOTAlign: Semi-Supervised Alignment of Unimodal Vision and Language Models via Optimal Transport
Semi-supervised alignment of vision and language models using optimal transport with minimal paired samples.
2/27/2026
A Dataset is Worth 1 MB
Dataset compression approach enabling efficient distribution of training data to clients with limited hardware resources.
2/27/2026
Survey on Neural Routing Solvers
Survey of neural routing solvers using deep learning to replace handcrafted heuristics for vehicle routing optimization problems.
2/27/2026
SQaLe: A Large Text-to-SQL Corpus Grounded in Real Schemas
Large-scale text-to-SQL dataset (SQaLe) with 135k+ database schemas for training generalizable natural language to SQL conversion models.
2/27/2026
SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
Query-aware chunk compression method for RAG systems that dynamically optimizes document retrieval and generation based on input queries.
2/27/2026
CrossLLM-Mamba: Multimodal State Space Fusion of LLMs for RNA Interaction Prediction
Multimodal fusion of biological LLMs with state space models for improved RNA interaction prediction.
2/27/2026
Self-Purification Mitigates Backdoors in Multimodal Diffusion Language Models
Analysis of backdoor vulnerabilities in multimodal diffusion language models with self-purification defense mechanism.
2/27/2026
FIRE: A Comprehensive Benchmark for Financial Intelligence and Reasoning Evaluation
Benchmark evaluating LLMs on financial knowledge through exam questions and practical business reasoning scenarios.
2/27/2026
RETLLM: Training and Data-Free MLLMs for Multimodal Information Retrieval
Training-free framework for multimodal information retrieval using MLLMs without large datasets or pre-training fine-tuning.
2/27/2026
What Topological and Geometric Structure Do Biological Foundation Models Learn? Evidence from 141 Hypotheses
Large-scale hypothesis screening of biological foundation models to understand what geometric and topological structures they learn from gene expression data.
2/27/2026
Decoding the Hook: A Multimodal LLM Framework for Analyzing the Hooking Period of Video Ads
Multimodal LLM framework analyzing video ad effectiveness by examining the first three seconds using visual, audio, and text analysis.
2/27/2026
Causality $\neq$ Invariance: Function and Concept Vectors in LLMs
Analysis of function vectors in LLMs showing they lack invariance across input formats despite targeting same concepts.
2/27/2026
SimpleOCR: Rendering Visualized Questions to Teach MLLMs to Read
Testing framework to diagnose whether MLLMs genuinely read text in images or rely on parametric shortcuts in prompts.
2/27/2026
GetBatch: Distributed Multi-Object Retrieval for ML Data Loading
GetBatch: Object store API elevating batch retrieval to first-class operation for efficient ML data loading across storage clusters.
2/27/2026
veScale-FSDP: Flexible and High-Performance FSDP at Scale
veScale-FSDP: Enhanced FSDP distributed training framework supporting block-wise quantization and non-element-wise optimizers.
2/27/2026
How Do Latent Reasoning Methods Perform Under Weak and Strong Supervision?
Empirical study of latent reasoning methods under weak and strong supervision for multi-step LLM reasoning.
2/27/2026
When to Act, Ask, or Learn: Uncertainty-Aware Policy Steering
Uncertainty-aware policy steering using VLM verifiers to adapt robot behaviors by selecting aligned action samples.
2/27/2026
VeRO: An Evaluation Harness for Agents to Optimize Agents
VeRO: Evaluation framework for assessing coding agents that optimize other agents through iterative edit-execute-evaluate cycles.
2/27/2026
Flow Matching is Adaptive to Manifold Structures
Flow matching generative model that adapts to manifold structures, offering simulation-free alternative to diffusion models.
2/27/2026
From Shallow Bayesian Neural Networks to Gaussian Processes: General Convergence, Identifiability and Scalable Inference
Theoretical analysis of scaling limits from shallow Bayesian neural networks to Gaussian processes with scalable inference methods.
2/27/2026
Towards Dynamic Dense Retrieval with Routing Strategy
Dynamic dense retrieval with routing strategy for adapting information retrieval models across domains without full retraining.
2/27/2026
CourtGuard: A Model-Agnostic Framework for Zero-Shot Policy Adaptation in LLM Safety
CourtGuard: Model-agnostic multi-agent framework for zero-shot LLM safety policy adaptation using retrieval-augmented debate.
2/27/2026
Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
Search-P1: Path-centric reward shaping for training agentic RAG systems with improved sample efficiency via RL.
2/27/2026
Correcting Human Labels for Rater Effects in AI Evaluation: An Item Response Theory Approach
Item Response Theory approach to correct systematic rater biases in human evaluations for AI model assessment.
2/27/2026
SideQuest: Model-Driven KV Cache Management for Long-Horizon Agentic Reasoning
SideQuest: Model-driven KV cache management technique for long-context agentic reasoning tasks with multi-hop retrieval.
2/27/2026
Advancing accelerator virtual beam diagnostics through latent evolution modeling: an integrated solution to forward, inverse, tuning, and UQ problems
Hybrid ML framework combining autoencoders and transformers for accelerator beam diagnostics simulations.
2/27/2026
Vectorizing the Trie: Efficient Constrained Decoding for LLM-based Generative Retrieval on Accelerators
Trie-based constrained decoding optimization for LLM generative retrieval on accelerators. Improves business logic constraints in recommendations.
2/27/2026
dLLM: Simple Diffusion Language Modeling
dLLM: Unified framework for diffusion language models. Standardizes components across research implementations for reproducibility.
2/27/2026
Generative Recommendation for Large-Scale Advertising
GR4AD: Production generative recommendation system for large-scale advertising using LLMs. Architecture, learning, and serving optimization.