3/25/2026
Hyperagents – Self-referential self-improving agents
Self-referential AI agents that optimize themselves for arbitrary computable tasks with experiment logging and code generation.
3/25/2026
Show HN: I've ditched paper todo lists
Shared household task planner separating undated and dated tasks for household management.
3/25/2026
Show HN: Chronos a Drag-and-Drop Scheduler
Chronos is a drag-and-drop task scheduler with UI-first design, built with AI assistance.
3/25/2026
I built a free on-device photo search for Windows – natural language, no cloud
Local Windows application for natural language photo search without cloud uploads, processing terabytes on-device.
3/25/2026
Show HN: Vesper – MCP-native tool that automates dataset prep for AI agents
Vesper is an MCP-native tool enabling AI agents to autonomously search, download, clean, and export datasets from Kaggle, HuggingFace, and OpenML without human intervention.
3/25/2026
Welcome to IBM Bob: Your AI-Powered Development Partner
IBM Bob is an AI development partner integrated into codebases with customizable modes for code assistance and quality improvements.
3/25/2026
ToolTrust Scanner – detect backdoored MCP packages (litellm 1.82.8)
ToolTrust Scanner detects security vulnerabilities in MCP packages, including prompt injection and supply chain exploits, before AI agents execute them.
3/25/2026
Show HN: Pixelbeat – A pixel-art terminal music player daemon written in Rust
Pixelbeat is a Rust-based terminal music player daemon with pixel-art UI for coding sessions.
3/25/2026
Ask HN: Is anyone here giving their MCP server a code execution environment?
Discussion on giving MCP servers code execution capability to handle complex data processing tasks like analyzing high-frequency wearable sensor streams without manual aggregation.
3/25/2026
CRP: An Open Protocol for Multi-Threaded Cognitive Perception in AI Systems
Proposal for an open protocol called CRP for cognitive perception in AI systems with pattern recognition capabilities.
3/25/2026
Using AI as a Design Engineer
Personal experience using AI as a design engineering tool for experimentation and iterative refinement in creative work.
3/25/2026
Beyond Preset Identities: How Agents Form Stances and Boundaries in Generative Societies
Framework for studying how LLM-based agents form stable stances and identities in multiagent communities using virtual ethnography methods.
3/25/2026
Bilevel Autoresearch: Meta-Autoresearching Itself
Bilevel autoresearch applying automated research loops to optimize autoresearch systems themselves, improving bottlenecks iteratively.
3/25/2026
Automated Microservice Pattern Instance Detection Using Infrastructure-as-Code Artifacts and Large Language Models
Using LLMs to detect microservice architecture patterns from Infrastructure-as-Code artifacts for documentation purposes.
3/25/2026
Founder effects shape the evolutionary dynamics of multimodality in open LLM families
Analysis of 1.8M Hugging Face models tracking how multimodal capabilities emerge and propagate across open LLM families.
3/25/2026
Evaluating Prompting Strategies for Chart Question Answering with Large Language Models
Systematic evaluation of four prompting strategies across GPT models on chart-based question answering, isolating prompt structure effects.
3/25/2026
MERIT: Memory-Enhanced Retrieval for Interpretable Knowledge Tracing
MERIT system combining memory and retrieval mechanisms with LLMs for interpretable knowledge tracing in educational settings.
3/25/2026
Beyond Hard Constraints: Budget-Conditioned Reachability For Safe Offline Reinforcement Learning
Safety-constrained offline reinforcement learning using reachability analysis for sequential decision making in real-world applications.
3/25/2026
TIPS: Turn-Level Information-Potential Reward Shaping for Search-Augmented LLMs
TIPS framework for training search-augmented LLMs with reinforcement learning, improving credit assignment and reward shaping for question answering tasks.
3/25/2026
Efficient Embedding-based Synthetic Data Generation for Complex Reasoning Tasks
Methods for generating high-quality synthetic training data using LLMs to fine-tune smaller models, analyzing diversity and distribution in embedding space.
3/25/2026
Whether, Not Which: Mechanistic Interpretability Reveals Dissociable Affect Reception and Emotion Categorization in LLMs
Mechanistic interpretability study investigating whether LLMs develop genuine emotional representations or merely detect emotion keywords through circuit analysis.
3/25/2026
Between the Layers Lies the Truth: Uncertainty Estimation in LLMs Using Intra-Layer Local Information Scores
Compact uncertainty estimation method for LLMs scoring cross-layer agreement patterns in internal representations via single forward pass.
3/25/2026
Scaling Attention via Feature Sparsity
Sparse Feature Attention method reducing transformer self-attention cost via k-sparse feature representations instead of sequence-level sparsity.
3/25/2026
Latent Semantic Manifolds in Large Language Models
Mathematical framework interpreting LLM hidden states as points on latent semantic manifolds with Riemannian geometry and Voronoi partitions.
3/25/2026
Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
Training-free hallucination detector for LLMs using sample transform cost to measure output distribution complexity without fine-tuning.
3/25/2026
CN-Buzz2Portfolio: A Chinese-Market Dataset and Benchmark for LLM-Based Macro and Sector Asset Allocation from Daily Trending Financial News
Chinese financial news dataset and benchmark for evaluating LLM-based agents in macro and sector asset allocation decision-making.
3/25/2026
UniFluids: Unified Neural Operator Learning with Conditional Flow-matching
Conditional flow-matching framework using diffusion Transformers to unify learning of PDE solution operators across varying dimensionality.
3/25/2026
A Multi-Modal CNN-LSTM Framework with Multi-Head Attention and Focal Loss for Real-Time Elderly Fall Detection
CNN-LSTM framework with attention and focal loss for detecting falls in elderly individuals from multimodal sensor data.
3/25/2026
Enhancing AI-Based Tropical Cyclone Track and Intensity Forecasting via Systematic Bias Correction
AI-based tropical cyclone track and intensity forecasting with systematic bias correction on weather data.
3/25/2026
Emergency Preemption Without Online Exploration: A Decision Transformer Approach
Decision Transformer approach for optimizing emergency vehicle signal preemption using offline, return-conditioned sequence modeling.
3/25/2026
ST-GDance++: A Scalable Spatial-Temporal Diffusion for Long-Duration Group Choreography
Diffusion model for generating synchronized group dance choreography from music with spatial coordination for film/gaming.
3/25/2026
Geometric Mixture-of-Experts with Curvature-Guided Adaptive Routing for Graph Representation Learning
Geometric Mixture-of-Experts framework for graph representation learning using curvature-guided routing on heterogeneous topologies.
3/25/2026
Sparsely-Supervised Data Assimilation via Physics-Informed Schr\"odinger Bridge
Physics-informed Schrödinger bridge approach for data assimilation from sparse observations in PDE-governed systems.
3/25/2026
From Instructions to Assistance: a Dataset Aligning Instruction Manuals with Assembly Videos for Evaluating Multimodal LLMs
Dataset aligning instruction manuals with assembly videos for evaluating multimodal LLMs on real-world technical tasks.
3/25/2026
AEGIS: An Operational Infrastructure for Post-Market Governance of Adaptive Medical AI Under US and EU Regulations
AEGIS infrastructure for governance of adaptive medical AI systems under FDA and EU regulations with continuous improvement.
3/25/2026
A Multi-Task Targeted Learning Framework for Lithium-Ion Battery State-of-Health and Remaining Useful Life
Multi-task deep learning framework for predicting lithium-ion battery state-of-health and remaining useful life.
3/25/2026
DAQ: Delta-Aware Quantization for Post-Training LLM Weight Compression
Delta-Aware Quantization framework for post-training LLM compression that preserves knowledge from alignment fine-tuning.
3/25/2026
A Direct Classification Approach for Reliable Wind Ramp Event Forecasting under Severe Class Imbalance
Classification approach for wind power ramp event forecasting under severe class imbalance for grid stability.
3/25/2026
AgentSLR: Automating Systematic Literature Reviews in Epidemiology with Agentic AI
AgentSLR uses agentic AI to automate systematic literature reviews in epidemiology from retrieval through synthesis.
3/25/2026
Trained Persistent Memory for Frozen Decoder-Only LLMs
Method for adding trained persistent memory to frozen decoder-only LLMs without cross-attention mechanisms.
3/25/2026
Conformal Risk Control for Safety-Critical Wildfire Evacuation Mapping: A Comparative Study of Tabular, Spatial, and Graph-Based Models
Applies conformal prediction for formal safety guarantees in wildfire spread prediction using tabular, spatial, and graph models.
3/25/2026
Large Language Models for Missing Data Imputation: Understanding Behavior, Hallucination Effects, and Control Mechanisms
Comprehensive study of LLM-based data imputation across multiple models and datasets, analyzing hallucination effects and control mechanisms.
3/25/2026
Graph Signal Processing Meets Mamba2: Adaptive Filter Bank via Delta Modulation
Combines graph signal processing with Mamba2 state-space models to create adaptive filter banks for language modeling.
3/25/2026
Causal Direct Preference Optimization for Distributionally Robust Generative Recommendation
Causal Direct Preference Optimization method for training LLMs to generate recommendations while mitigating spurious correlations.
3/25/2026
Graphs RAG at Scale: Beyond Retrieval-Augmented Generation With Labeled Property Graphs and Resource Description Framework for Complex and Unknown Search Spaces
Graph RAG framework combining labeled property graphs and RDF for retrieval-augmented generation over structured and semi-structured data.
3/25/2026
T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search
T-MAP uses evolutionary search to red-team LLM agents by exploiting multi-step tool execution vulnerabilities in MCP ecosystems.
3/25/2026
First-Mover Bias in Gradient Boosting Explanations: Mechanism, Detection, and Resolution
Analysis of feature importance bias in gradient boosting models under multicollinearity, affecting SHAP-based explanations.
3/25/2026
WIST: Web-Grounded Iterative Self-Play Tree for Domain-Targeted Reasoning Improvement
WIST framework uses web-grounded iterative self-play with reinforcement learning to improve LLM reasoning in specific domains.
3/25/2026
Bridging neuroscience and AI: adaptive, culturally sensitive technologies transforming aphasia rehabilitation
Review of neuroscience and language technologies for aphasia rehabilitation using personalized, culturally sensitive AI tools.
3/25/2026
Unveiling the Mechanism of Continuous Representation Full-Waveform Inversion: A Wave Based Neural Tangent Kernel Framework
Theoretical analysis of full-waveform inversion using neural tangent kernel framework for geophysical and medical imaging.