2/25/2026
MoltMemory – AI agent memory for Moltbook
MoltMemory Python library adds persistent session memory and CAPTCHA solving to OpenClaw agents on Moltbook platform.
2/25/2026
Show HN: AgentVoice – Get feedback from AI to improve your MCP
AgentVoice tool enables API providers to receive structured feedback from AI agents (Claude Code, Cursor) via MCP, identifying friction points in agent-API interactions.
2/25/2026
Cache-aware prefill–decode disaggregation for 40% faster LLM serving
Research: Cache-aware prefill-decode disaggregation (CPD) architecture for 40% faster LLM serving by separating cold/warm workloads via distributed KV cache.
2/25/2026
Show HN: claude-env – Manage multiple accounts for Claude-code
Open-source tool enabling multi-account management for Claude Code with separate environments, credentials, and settings per account.
2/25/2026
Show HN: Sopho - Open Source Business Intelligence Platform
Sopho: open-source BI/analytics platform with notebooks, SQL cells, dashboards, and AI-powered features addressing gaps in OSS offerings.
2/25/2026
The command line didn't die. It was waiting
Essay on the command line's evolution and relevance in modern development, reflecting on experiences with Claude Code as a developer tool.
2/25/2026
Show HN: PickOrCraft – AI photo studio, train your model, any aesthetic
PickOrCraft: AI image generation tool allowing users to train private models on personal photos with style customization and caption generation.
2/25/2026
Bullshit Benchmark Explorer
Interactive benchmark tool showing how well LLMs detect nonsense across questions, with color-coded responses (green/amber/red) and filtering capabilities.
2/25/2026
Pipeline Parallelism in SGLang: Scaling to Million-Token Contexts
SGLang implements optimized pipeline parallelism for million-token context inference using chunked parallelism, asynchronous communication, and dynamic chunking mechanisms.
2/25/2026
Show HN: Context Mode – 315 KB of MCP output becomes 5.4 KB in Claude Code
MCP server that compresses tool outputs for Claude Code by processing them in sandboxes and returning summaries, reducing 315 KB context to 5.4 KB and extending session time from 30 min to 3 hours.
2/25/2026
Show HN: Factagora – AI agents compete on predictions, time proves who's right
Platform where AI agents make predictions on factual claims scored by temporal accuracy rather than self-reporting, using Temporal Knowledge Graph.
2/25/2026
GPT-OSS Optimizations on Nvidia Blackwell: Pushing the Pareto Frontier
vLLM and Nvidia achieved +38% throughput and +13% latency improvements on GPT-OSS-120B using Blackwell GPUs via FlashInfer and torch.compile optimizations.
2/25/2026
Show HN: Riverse – Local AI agent with memory that grows over time
Local AI agent with persistent memory using River Algorithm to store facts, timelines, and confidence levels without cloud dependency.
2/25/2026
Show HN: AgentPass – Identity layer for AI agents (passports, email, trust)
AgentPass provides cryptographic identity and authentication infrastructure for autonomous AI agents. Identity layer enabling agent autonomy.
2/25/2026
Agent context management: ephemeral vs. durable classification
Relay product for efficient agent context management via ephemeral/durable classification. Token optimization for autonomous agents.
2/25/2026
AI_ATTRIBUTION.md: A Standard for Tracking Creative Control in Human-AI Coding
Standard for tracking human-AI creative control attribution in code generation. Developer tool for documentation and collaboration.
2/25/2026
vLLM WideEP and Large-Scale Serving Toward Maturity on Blackwell (Part I)
vLLM optimization achieving 26.2K prefill and 10.1K decode throughput on NVIDIA Blackwell for DeepSeek MoE models. Production LLM serving research.
2/25/2026
Webgrid Eval: LLM vision + tool-use on Neuralink's cursor control task
Benchmark for evaluating LLM vision and tool-use on cursor control task based on Neuralink's Webgrid test. Measures multimodal agent capabilities.
2/25/2026
I rebuilt Game Boy on web using 1 prompt and 5 parallel agents in 48 hours
Multi-agent autonomous workflow built Game Boy GBA emulator in 48 hours using TypeScript. Demonstrates agent orchestration and tool use.
2/25/2026
DataClaw: Publish your Claude Code chats to HuggingFace with a single command
DataClaw tool exports Claude Code conversation history to HuggingFace datasets. Data extraction tool with open source intent.
2/25/2026
Anthropic accuses DeepSeek and other Chinese rivals of mass data theft
News article about Anthropic accusing Chinese AI firms of model distillation for IP theft. Industry news, not technical content.
2/25/2026
Semantic Parallelism: Redefining Efficient MoE Inference via Model-Data Co-Scheduling
Semantic parallelism optimization for efficient MoE model inference across multiple devices.
2/25/2026
Diffusion Generative Recommendation with Continuous Tokens
Diffusion-based recommendation system using continuous tokens with LLM integration.
2/25/2026
How much does context affect the accuracy of AI health advice?
Evaluation of LLM accuracy for health advice across languages and contextual factors.
2/25/2026
MARVEL: Multi-Agent RTL Vulnerability Extraction using Large Language Models
Multi-agent system using LLMs to detect vulnerabilities in hardware RTL design specifications.
2/25/2026
HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning
Multimodal LLM combining vision, audio, and sensor data for embodied AI agents in smart homes.
2/25/2026
HSSBench: Benchmarking Humanities and Social Sciences Ability for Multimodal Large Language Models
Benchmark for evaluating multimodal LLM capabilities in humanities and social sciences requiring interdisciplinary reasoning.
2/25/2026
DesignBench: A Comprehensive Benchmark for MLLM-based Front-end Code Generation
Comprehensive benchmark for evaluating multimodal LLMs on front-end code generation from visual designs using modern frameworks.
2/25/2026
Towards Robust Real-World Multivariate Time Series Forecasting: A Unified Framework for Dependency, Asynchrony, and Missingness
Framework addressing dependency, asynchrony, and missing values in multivariate time series forecasting from real-world data.
2/25/2026
K-Function: Joint Pronunciation Transcription and Feedback for Evaluating Kids Language Function
LLM-based framework for evaluating children's language function through phonetic transcription and automated speech assessment.
2/25/2026
Characterizing State Space Model and Hybrid Language Model Performance with Long Context
Characterization and comparison of State Space Models and hybrid architectures versus Transformers for long-context processing on edge devices.
2/25/2026
Monte Carlo Tree Diffusion with Multiple Experts for Protein Design
Monte Carlo tree diffusion with multiple experts for protein sequence design combining masked diffusion models with tree search.
2/25/2026
RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility
Framework using LLMs as spatio-temporal predictors with hierarchical temporal tokenization for human mobility and trajectory prediction.
2/25/2026
Polychromic Objectives for Reinforcement Learning
Reinforcement learning fine-tuning approach using polychromic objectives to prevent policy collapse and maintain behavioral diversity.
2/25/2026
LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts
Learnable dynamic routing mechanism for mixture-of-experts with LoRA adapters enabling efficient LLM task adaptation without fixed expert assignment.
2/25/2026
PCPO: Proportionate Credit Policy Optimization for Aligning Image Generation Models
Policy optimization method for text-to-image models addressing credit assignment instability in reinforcement learning fine-tuning.
2/25/2026
On Robustness of Vision-Language-Action Model against Multi-Modal Perturbations
Evaluation of Vision-Language-Action model robustness against multi-modal perturbations across 17 adversarial conditions.
2/25/2026
AgentDR: Dynamic Recommendation with Implicit Item-Item Relations via LLM-based Agents
LLM-based agent framework for recommendation systems that leverages commonsense reasoning to capture item relationships and user intent.
2/25/2026
Everything is Plausible: Investigating the Impact of LLM Rationales on Human Notions of Plausibility
Study on how LLM-generated rationales influence human plausibility judgments in commonsense reasoning tasks using 3,000 human and 13,600 LLM judgments.
2/25/2026
Latent-Augmented Discrete Diffusion Models
Latent-Augmented Discrete Diffusion model improving fast language generation by modeling cross-token dependencies.
2/25/2026
Towards Scalable Oversight via Partitioned Human Supervision
Method for scalable AI oversight via partitioned human supervision across multiple domain experts for complex multi-domain tasks.
2/25/2026
Breaking Agent Backbones: Evaluating the Security of Backbone LLMs in AI Agents
Security evaluation framework for LLM backbone models in AI agents, addressing vulnerabilities unique to agent architectures.
2/25/2026
A Survey of Data Agents: Emerging Paradigm or Overstated Hype?
Survey examining terminology, definitions, and taxonomy of data agents—autonomous systems orchestrating data and AI for complex data tasks.
2/25/2026
Repurposing Synthetic Data for Fine-grained Search Agent Supervision
LLM-based search agents trained on synthetic entity-centric data using improved reward mechanisms to capture informative near-miss samples.
2/25/2026
OckBench: Measuring the Efficiency of LLM Reasoning
OckBench: Benchmark measuring LLM reasoning efficiency via token usage, revealing up to 5x differences in token length across models.
2/25/2026
Less is More: Data-Efficient Adaptation for Controllable Text-to-Video Generation
Data-efficient fine-tuning strategy for adding controllable parameters to text-to-video diffusion models using synthetic data.
2/25/2026
Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
Refusal Steering: Inference-time method for fine-grained control over LLM refusal behavior on sensitive topics without retraining.
2/25/2026
HiGR: Efficient Generative Slate Recommendation via Hierarchical Planning and Multi-Objective Preference Alignment
HiGR: Generative slate recommendation system using hierarchical planning and multi-objective preference alignment for ranked lists.
2/25/2026
CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
CogFlow: Multimodal LLM system for visual math problem solving improving visual perception integration and reasoning.
2/25/2026
What Matters For Safety Alignment?
Comprehensive empirical study evaluating factors affecting safety alignment in LLMs and LRMs across 32 recent models.