BLakshmiSahithi/Adversarial-Multi-Agent-Deliberation-Framework
Adversarial multi-agent debate framework — hallucination mitigation, citation-verified scoring, explainable audit trails, role-locked adversarial prompting, quantamental signal validation, evaluation and LangSmith observability. Demonstrated on financial risk analysis.
SUMMARY AI summary by gpt-5-mini
A domain-agnostic multi-agent framework that externalizes and auditable-izes LLM reasoning for regulated decisions (investment committees, fraud adjudication, credit decisioning, compliance review). It fetches structured data, runs a pure‑Python "quantamental" analyst to produce a tagged intelligence brief, then executes an adversarial debate loop: Bull and Bear agents argue using only tagged observations; a non-LLM Fact-Checker verifies citations and computes a deterministic support score; Challenger and Rebuttal agents probe weaknesses. A Calibration Engine normalizes scores and a Judge issues a verdict from verified claims only. Key features: citation-level traceability, deterministic scoring (including high-weight QUANT_ALERTs from cross-signal validation), hallucination mitigation with rewrite/penalty rules, role enforcement for adversarial behavior, and production observability.
DETECTED Detected AI stack
AI-related keywords found in this repo's description, topics, or README summary — grouped by category. Each badge links to the corresponding ranking detail page.
Language breakdown (by bytes)
Owner
Dates
| Created on GitHub | 2026-05-18 |
| Last push | 2026-05-18 |
| First seen here | 2026-05-18 |
| Last fetched | 2026-05-19 16:17 |
Similar repos (same language)
Reverse proxy for your ai quota from the SW platform.
dea6cat/2b-agentThis llm Agent was created based on necessity for one that could simply use local models without making them hallucinate and keep them focus
Zuboy/Carbon-Cost-Optimizer-Agentic-AIAn AI agent that decides where and when to run ML training jobs to minimize cost and carbon emissions, then launches them autonomously — exposed entirely through MCP tools.
FuchaZ/lm-studio-vision-bridge给纯文本 AI agent 装上眼睛——通过 LM Studio 本地视觉模型提供 MCP 图片识别服务
Shrutirowlo/AI-Video-AgentAI-powered video generation agent that automates script analysis, scene planning, and video creation.
Shivang0/social-visionPaste an Instagram/TikTok/YouTube/X link and Claude watches it for you — transcribes audio, reads on-screen text & visuals, explains what it's about. Local, cross-platform Claude Code plugin.
markusbegerow/claude-fuer-oeffentliche-verwaltung⚠️ Experimentelle Skill-Sammlung für Digitalisierung, Fachverfahren und Organisation der deutschen öffentlichen Verwaltung (OZG, FIM, FIT-Connect, KI-Einsatz, eIDAS, BSI-IT-Grundschutz, DSGVO) – bitte testen, Issues/PRs willkommen! Keine Rechts-/Datenschutzberatung, keine verbindliche Behördenentscheidung. Keine Bürger-/Mitarbeiterdaten im Repo.
knowledgegut/course-distiller把有權使用的工作坊/課程回放消化成套品牌色的步驟式學習 PDF；最後的重組交還人腦。A Claude Code skill by 知識包小腸.