Agent coordination resources: A2A, MCP, HCT signaling protocols, CAMEL, IoA orchestration patterns for multi-agent systems.
AI & ML interests
AI Research & Engineering · Multi-Agent System Coordination
Recent Activity
RAG architectures, hierarchical memory, semantic chunking, query rewriting, context compression for agents.
-
microsoft/ms_marco
Viewer • Updated • 1.11M • 12.9k • 220 -
sentence-transformers/all-nli
Viewer • Updated • 2.86M • 3.93k • 47 -
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Paper • 2005.11401 • Published • 14 -
Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models
Paper • 2402.04614 • Published • 3
LLM tool use: Toolformer, ReAct, MCP protocol, dynamic tool selection, autonomous agent execution loops.
-
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 612k • • 592 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 12M • • 5.25k -
Toolformer: Language Models Can Teach Themselves to Use Tools
Paper • 2302.04761 • Published • 12 -
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 31
CoT, ToT, GoT, ReAct, ReWOO prompting techniques for LLM reasoning with implementation guidance and benchmarks.
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 379k • • 12.9k -
Qwen/Qwen2.5-Coder-32B-Instruct
Text Generation • 33B • Updated • 373k • • 1.97k -
google/gemma-2-27b-it
Text Generation • 27B • Updated • 539k • 556 -
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Paper • 2201.11903 • Published • 15
LLM degradation detection, hallucination research, probe-based testing, model collapse, quality monitoring tools.
AI agent security: prompt injection defense, jailbreak detection, guardrails, constitutional AI, zero trust architecture.
-
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 32.7k • • 257 -
Jailbroken: How Does LLM Safety Training Fail?
Paper • 2307.02483 • Published • 14 -
Constitutional AI: Harmlessness from AI Feedback
Paper • 2212.08073 • Published • 4 -
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Paper • 2312.06674 • Published • 8
Agent coordination resources: A2A, MCP, HCT signaling protocols, CAMEL, IoA orchestration patterns for multi-agent systems.
CoT, ToT, GoT, ReAct, ReWOO prompting techniques for LLM reasoning with implementation guidance and benchmarks.
-
deepseek-ai/DeepSeek-R1
Text Generation • 685B • Updated • 379k • • 12.9k -
Qwen/Qwen2.5-Coder-32B-Instruct
Text Generation • 33B • Updated • 373k • • 1.97k -
google/gemma-2-27b-it
Text Generation • 27B • Updated • 539k • 556 -
Chain-of-Thought Prompting Elicits Reasoning in Large Language Models
Paper • 2201.11903 • Published • 15
RAG architectures, hierarchical memory, semantic chunking, query rewriting, context compression for agents.
-
microsoft/ms_marco
Viewer • Updated • 1.11M • 12.9k • 220 -
sentence-transformers/all-nli
Viewer • Updated • 2.86M • 3.93k • 47 -
Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
Paper • 2005.11401 • Published • 14 -
Faithfulness vs. Plausibility: On the (Un)Reliability of Explanations from Large Language Models
Paper • 2402.04614 • Published • 3
LLM degradation detection, hallucination research, probe-based testing, model collapse, quality monitoring tools.
LLM tool use: Toolformer, ReAct, MCP protocol, dynamic tool selection, autonomous agent execution loops.
-
Qwen/Qwen2.5-Coder-7B-Instruct
Text Generation • 8B • Updated • 612k • • 592 -
meta-llama/Llama-3.1-8B-Instruct
Text Generation • 8B • Updated • 12M • • 5.25k -
Toolformer: Language Models Can Teach Themselves to Use Tools
Paper • 2302.04761 • Published • 12 -
ReAct: Synergizing Reasoning and Acting in Language Models
Paper • 2210.03629 • Published • 31
AI agent security: prompt injection defense, jailbreak detection, guardrails, constitutional AI, zero trust architecture.
-
meta-llama/Llama-Guard-3-8B
Text Generation • 8B • Updated • 32.7k • • 257 -
Jailbroken: How Does LLM Safety Training Fail?
Paper • 2307.02483 • Published • 14 -
Constitutional AI: Harmlessness from AI Feedback
Paper • 2212.08073 • Published • 4 -
Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations
Paper • 2312.06674 • Published • 8