This shows you the differences between two versions of the page.
| Both sides previous revisionPrevious revisionNext revision | Previous revision | ||
| sidebar [2026/03/24 17:10] – Update sidebar with all 24 new pages agent | sidebar [2026/03/24 22:04] (current) – Trim sidebar to curated ~70 entries, add All Pages link agent | ||
|---|---|---|---|
| Line 9: | Line 9: | ||
| * [[agent_safety|Agent Safety]] | * [[agent_safety|Agent Safety]] | ||
| - | **Reasoning | + | **Reasoning** |
| * [[chain_of_thought|Chain-of-Thought]] | * [[chain_of_thought|Chain-of-Thought]] | ||
| * [[tree_of_thoughts|Tree of Thoughts]] | * [[tree_of_thoughts|Tree of Thoughts]] | ||
| + | * [[graph_of_thoughts|Graph of Thoughts]] | ||
| * [[react_framework|ReAct]] | * [[react_framework|ReAct]] | ||
| * [[reflexion_framework|Reflexion]] | * [[reflexion_framework|Reflexion]] | ||
| - | * [[prompt_chaining|Prompt Chaining]] | + | * [[self_consistency|Self-Consistency]] |
| - | * [[prompt_engineering|Prompt Engineering]] | + | |
| * [[latent_reasoning|Latent Reasoning]] | * [[latent_reasoning|Latent Reasoning]] | ||
| * [[test_time_compute_scaling|Test-Time Compute]] | * [[test_time_compute_scaling|Test-Time Compute]] | ||
| + | * [[prompt_engineering|Prompt Engineering]] | ||
| - | **Memory | + | **Memory |
| * [[hierarchical_memory|Hierarchical Memory]] | * [[hierarchical_memory|Hierarchical Memory]] | ||
| - | * [[short_term_memory|Short-Term]] | ||
| - | * [[long_term_memory|Long-Term]] | ||
| - | * [[memory_augmentation_strategies|Augmentation]] | ||
| - | * [[agent_memory_frameworks|Memory Frameworks]] | ||
| * [[retrieval_augmented_generation|RAG]] | * [[retrieval_augmented_generation|RAG]] | ||
| + | * [[agentic_rag|Agentic RAG]] | ||
| * [[knowledge_graphs|Knowledge Graphs]] | * [[knowledge_graphs|Knowledge Graphs]] | ||
| * [[embeddings|Embeddings]] | * [[embeddings|Embeddings]] | ||
| - | * [[continual_learning_agents|Continual Learning]] | ||
| - | |||
| - | **Retrieval** | ||
| * [[faiss|FAISS]] | * [[faiss|FAISS]] | ||
| - | * [[hnsw_graphs|HNSW]] | ||
| - | * [[scann|ScaNN]] | ||
| **Agent Types** | **Agent Types** | ||
| * [[autonomous_agents|Autonomous]] | * [[autonomous_agents|Autonomous]] | ||
| * [[react_agents|ReAct Agents]] | * [[react_agents|ReAct Agents]] | ||
| - | * [[plan_and_execute_agents|Plan & Execute]] | ||
| - | * [[conversational_agents|Conversational]] | ||
| - | * [[tool_using_agents|Tool-Using]] | ||
| * [[code_generation_agents|Code Agents]] | * [[code_generation_agents|Code Agents]] | ||
| * [[web_browsing_agents|Web Browsing]] | * [[web_browsing_agents|Web Browsing]] | ||
| - | * [[vision_agents|Vision | + | * [[vision_agents|Vision]] |
| - | * [[voice_agents|Voice | + | * [[voice_agents|Voice]] |
| - | * [[ai_scientist_agents|AI Scientists]] | + | * [[generative_agents|Generative Agents]] |
| - | * [[gui_grounding_agents|GUI Grounding]] | + | |
| - | * [[long_horizon_agents|Long-Horizon]] | + | |
| **Design Patterns** | **Design Patterns** | ||
| Line 53: | Line 41: | ||
| * [[agent_orchestration|Orchestration]] | * [[agent_orchestration|Orchestration]] | ||
| * [[multi_agent_systems|Multi-Agent]] | * [[multi_agent_systems|Multi-Agent]] | ||
| - | * [[modular_architectures|Modular Architectures]] | ||
| * [[function_calling|Function Calling]] | * [[function_calling|Function Calling]] | ||
| - | * [[tool_integration_patterns|Tool Integration]] | + | * [[modular_architectures|Modular]] |
| - | * [[parallel_function_calling|Parallel Calls]] | + | |
| - | * [[speculative_tool_execution|Speculative Execution]] | + | |
| * [[durable_execution_for_agents|Durable Execution]] | * [[durable_execution_for_agents|Durable Execution]] | ||
| - | * [[context_window_management|Context Management]] | + | * [[agent_cost_optimization|Cost Optimization]] |
| **Training & Alignment** | **Training & Alignment** | ||
| - | * [[rlhf|RLHF | + | * [[rlhf|RLHF]] |
| - | * [[agent_rlvr|RLVR]] | + | * [[direct_preference_optimization|DPO]] |
| - | * [[agentic_reinforcement_learning|Agentic RL]] | + | * [[constitutional_ai|Constitutional AI]] |
| * [[process_reward_models|Process Rewards]] | * [[process_reward_models|Process Rewards]] | ||
| - | * [[reasoning_reward_models|Reasoning Rewards]] | ||
| * [[fine_tuning_agents|Fine-Tuning]] | * [[fine_tuning_agents|Fine-Tuning]] | ||
| - | * [[agent_trajectory_optimization|Trajectory Optimization]] | + | * [[agent_distillation|Distillation]] |
| - | * [[world_models_for_agents|World Models]] | + | |
| - | * [[neurosymbolic_agents|Neurosymbolic]] | + | |
| **Frameworks** | **Frameworks** | ||
| * [[anthropic_context_protocol|MCP]] | * [[anthropic_context_protocol|MCP]] | ||
| - | * [[a2a_protocol|A2A | + | * [[a2a_protocol|A2A]] |
| * [[langgraph|LangGraph]] | * [[langgraph|LangGraph]] | ||
| * [[crewai|CrewAI]] | * [[crewai|CrewAI]] | ||
| Line 82: | Line 64: | ||
| * [[openai_agents_sdk|OpenAI Agents SDK]] | * [[openai_agents_sdk|OpenAI Agents SDK]] | ||
| * [[claude_agent_sdk|Claude Agent SDK]] | * [[claude_agent_sdk|Claude Agent SDK]] | ||
| - | * [[semantic_kernel|Semantic Kernel]] | ||
| - | * [[smolagents|Smolagents]] | ||
| * [[openhands|OpenHands]] | * [[openhands|OpenHands]] | ||
| - | * [[langroid|Langroid]] | ||
| - | * [[flowise|Flowise]] | ||
| - | * [[lite_llm|LiteLLM]] | ||
| - | * [[microsoft_graphrag|GraphRAG]] | ||
| - | **Tools | + | **Tools** |
| * [[devin|Devin]] | * [[devin|Devin]] | ||
| * [[cursor|Cursor]] | * [[cursor|Cursor]] | ||
| * [[claude_code|Claude Code]] | * [[claude_code|Claude Code]] | ||
| + | * [[aider|Aider]] | ||
| * [[computer_use|Computer Use]] | * [[computer_use|Computer Use]] | ||
| - | * [[bolt_new|Bolt.new]] | ||
| - | **Safety & Governance** | + | **Safety & Security** |
| - | * [[agent_sandbox_security|Sandbox Security]] | + | * [[agent_sandbox_security|Sandboxing]] |
| - | * [[agent_governance_frameworks|Governance]] | + | |
| * [[agent_threat_modeling|Threat Modeling]] | * [[agent_threat_modeling|Threat Modeling]] | ||
| + | * [[llm_hallucination|Hallucination]] | ||
| **Evaluation** | **Evaluation** | ||
| * [[agent_evaluation|Overview]] | * [[agent_evaluation|Overview]] | ||
| * [[swe_bench|SWE-bench]] | * [[swe_bench|SWE-bench]] | ||
| - | * [[web_arena_benchmark|WebArena]] | + | * [[gaia_benchmark|GAIA]] |
| - | * [[agent_as_a_judge|Agent-as-Judge]] | + | * [[agentbench|AgentBench]] |
| - | * [[agent_index|Agent Index]] | + | |
| - | **Development** | + | **[[all_pages|All Pages →]]** |
| - | | + | |
| - | | + | |
| **Meta** | **Meta** | ||
| * [[agents: | * [[agents: | ||