The OCI Agent Evaluation Framework goes beyond final-answer scoring to evaluate prompts, RAG, tools, trajectories, state changes, and production behavior across the agent lifecycle. Learn more:

📚 Wouldn't it be great to run ReAct, RAG, and Tree of Thoughts behind one API and compare them, instead of wrangling scattered per-paper implementations? This repo delivers exactly that, with all 35 patterns in one place. Title: FareedKhan-dev/all-agentic-architectures URL: 📦 Overview This is a Python library and a "living textbook" implementing 35 production-grade agentic AI patterns. Every architecture exposes the same .run(task) method and returns an identical result shape, so you can swap patterns without touching downstream code. ❓ Challenges Solved Agentic design patterns have been scattered across papers, each with its own implementation and conventions. The real value here is unifying them under a single interface so you can try them side by side. 💡 Core Idea & Approach The central idea is the "deterministic-picker discipline." ・Instead of handing scoring entirely to the LLM, it first has the LLM commit to categorical features like booleans and enums ・The final decision is then composed in Python logic This mitigates the flat-band pathology of LLM-as-Scorer, and it appears in 13 of the 35 architectures. 🎯 Coverage & Use Cases It spans eight families: reasoning and reflection (Reflection, Self-Discover), search (Tree of Thoughts, LATS), RAG (Corrective/Self/Adaptive/GraphRAG), memory (MemGPT, Voyager), tools and actions (ReAct, SWE-Agent), and multi-agent (Debate, STORM). Each pattern ships with an executed Jupyter notebook, giving reproducible references grounded in real LLM output. 📊 Highlights ・Built on LangGraph, with support for Nebius, OpenAI, Anthropic, Ollama and more, switchable via a single env var ・283 passing pytest tests ・On a 17-task benchmark it recently scored 33/42 correct (78%), with Reflection and Self-Consistency among the strongest #AIAgents# #LangGraph#

RAG's "more precision means more latency" dilemma, tackled by using topics as a compass 🧭 Title: MCompassRAG: Topic Metadata as a Semantic Compass for Paragraph-Level Retrieval URL: 🧭 Overview A metadata-guided retrieval framework that uses topic-level signals as a "semantic compass" to select relevant evidence at the paragraph level. It aims to improve precision and efficiency at the same time. ❓ Challenges Solved RAG faces a precision-vs-efficiency trade-off. ・Fine-grained chunks raise precision but increase candidates, latency, and cost ・Larger chunks reduce candidates but introduce semantic noise from mixed topics This is acute in deep-research tasks needing fast, precise retrieval over large datasets. 💡 Methodology & Proposed Approach ・It enriches chunk representations with topic metadata within the same embedding space ・It uses LLM-teacher distillation to train a lightweight retriever ・This enables topic-aware retrieval with no additional LLM calls at inference time The core is combining metadata with dense embeddings and distilling into a lightweight retriever. 📊 Experimental Results ・Information efficiency: 8.24% average improvement across six benchmarks ・Latency: over 5x lower than the strongest efficient RAG baselines ・Code is available in a public repository It achieves this precision-and-speed balance without extra LLM calls at inference. #RAG# #Retrieval#