self-evaluation

[ICLR 2025] Code and Data Repo for Paper "Latent Space Chain-of-Embedding Enables Output-free LLM Self-Evaluation"

AI agent self-reflection & self-evaluation tool. Built by an AI, for AIs.

Lightweight behavior control layer for LLM using latent state, reward, and self-evaluation (no training required)

A Telegram ChatBot for placement preparing aspirants to prepare for the upcoming placements.

Agentic self-evaluating lesson generator using LangGraph, LLM-based PASS/FAIL evaluation, retry feedback, and persistent memory.

Agentic content pipeline that generates a beginner lesson, evaluates it against a self-designed rubric, and regenerates on failure — built with LangGraph, Gemini, and Chroma. Deterministic pass/fail validation, not LLM self-report.

Maat Reflection – Extension for the text generation WebUI to add self-reflection, heuristics and improved reasoning

RAG-powered technical support system with self-evaluation pipeline and grading metrics

An agentic Self-RAG system that answers biomedical research-verification questions using a LangGraph pipeline — retrieves from PubMed abstracts, grades its own retrieval, checks for hallucination, and abstains when evidence is weak.

A cognitive agent architecture using LangGraph and Python custom orchestration for adaptive travel planning. Employs a non-destructive state machine with dynamic self-evaluation, conditional re-search loops to fix data gaps, and robust Streamlit UI persistence guards alongside token-optimized data serialization.