infiniflow/ragflow
Open-source RAG engine with agentic workflow capabilities. Combines retrieval-augmented generation with agent orchestration for enhanced LLM context.
Open-source RAG engine with agentic workflow capabilities. Combines retrieval-augmented generation with agent orchestration for enhanced LLM context.
Classical machine learning library in Python. Foundational ML tool but predates modern LLM applications and agent frameworks.
Technical deep-dive into how transformer architecture functions in LLMs, beyond surface-level explanations.
Python/TypeScript SDK enabling AI agents to share operational learnings via local SQLite storage with automatic PII redaction. Solves knowledge transfer between independent agents solving similar problems.
GLM 5 model (Pony Alpha) released and available for free tier usage, generating discussion in AI community.
Explores recursive approaches in language models, relevant to understanding advanced LLM architectures and how models can process hierarchical information iteratively.
Open source Python project for real-time face swapping and deepfake generation using GANs. Practical implementation of deep learning techniques.
Fine-tuning and reinforcement learning library optimized for LLMs. Reduces training time and memory for Llama, Qwen, Gemma, DeepSeek and other models.
Examines ethical failures in AI agents under performance pressure, showing how KPI optimization can cause agents to violate safety constraints.
Local-first memory system for AI assistants (Claude, ChatGPT, Cursor) that persists context across sessions without cloud costs or privacy tradeoffs. Addresses context amnesia problem in multi-session AI workflows.
Production LLM system management without losing control, covering embedded customer support and business applications.
Community-driven repository of ChatGPT and LLM prompts with self-hosting option. Reference collection for prompt engineering techniques.
Framework for designing constrained AI systems versus unconstrained ones. Applies software engineering principles to AI system architecture.
Utility library providing reusable patterns for GenLayer intelligent contracts. Combines AI with blockchain but limited mainstream relevance.
Addresses noise filtering in enterprise AI agents using RAS architecture. Focuses on system design patterns for reliable agent deployment.
E-commerce automation using n8n workflow tool. Business automation case study with LLM/prompt engineering as supporting component.
Comparison of five LLM gateway platforms for 2026 production use, addressing model selection beyond initial choice.
Tool for automating AI agent project setup and configuration to streamline development workflow.
Discusses why LLMs lack conversation memory and implications. Chinese/English bilingual article on fundamental LLM limitation.
Discovering Differences in Strategic Behavior Between Humans and LLMs
LiveMedBench: A Contamination-Free Medical Benchmark for LLMs with Automated Rubric Evaluation
Found-RL: foundation model-enhanced reinforcement learning for autonomous driving
MERIT Feedback Elicits Better Bargaining in LLM Negotiators
Abstraction Generation for Generalized Planning with Pretrained Large Language Models
Flow of Spans: Generalizing Language Models to Dynamic Span-Vocabulary via GFlowNets
Neuro-symbolic Action Masking for Deep Reinforcement Learning
To Think or Not To Think, That is The Question for Large Reasoning Models in Theory of Mind Tasks
OmniSapiens: A Foundation Model for Social Behavior Processing via Heterogeneity-Aware Relative Policy Optimization
Spend Search Where It Pays: Value-Guided Structured Sampling and Optimization for Generative Recommendation
Integrating Generative AI-enhanced Cognitive Systems in Higher Education: From Stakeholder Perceptions to a Conceptual Framework considering the EU AI Act
See, Plan, Snap: Evaluating Multimodal GUI Agents in Scratch
SynergyKGC: Reconciling Topological Heterogeneity in Knowledge Graph Completion via Topology-Aware Synergy
Reinforcing Chain-of-Thought Reasoning with Self-Evolving Rubrics
Can LLMs Cook Jamaican Couscous? A Study of Cultural Novelty in Recipe Generation
CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion
GameDevBench: Evaluating Agentic Capabilities Through Game Development
FormalJudge: A Neuro-Symbolic Paradigm for Agentic Oversight
Large Language Models Predict Functional Outcomes after Acute Ischemic Stroke
A Practical Guide to Agentic AI Transition in Organizations
"Humans welcome to observe": A First Look at the Agent Social Network Moltbook
The Anatomy of the Moltbook Social Graph
TokaMark: A Comprehensive Benchmark for MAST Tokamak Plasma Models
AgentTrace: A Structured Logging Framework for Agent System Observability
Reverse-Engineering Model Editing on Language Models
Multi-encoder ConvNeXt Network with Smooth Attentional Feature Fusion for Multispectral Semantic Segmentation
Multimodal Information Fusion for Chart Understanding: A Survey of MLLMs -- Evolution, Limitations, and Cognitive Enhancement
Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible
Can Large Language Models Implement Agent-Based Models? An ODD-based Replication Study
When LLMs get significantly worse: A statistical approach to detect model degradations
Silence Routing: When Not Speaking Improves Collective Judgment