R_REDDYX.XYZ
AIPython★ 280⑂ 37 forksApache-2.0

AIFrontierLab/AgentArk

AGENTARK: ONE LLM INSTEAD OF MANY AGENTS

Official AgentArk implementation from CMU and Georgia Tech. Method distills multi-agent intelligence into a single LLM agent preserving task quality. Python code, 260 GitHub stars.

// KEY FEATURES

  • Distills multi-agent intelligence into one LLM without quality loss
  • Trains single agent on interaction trajectories of multiple agents
  • NeurIPS'26 paper implementation from CMU and Georgia Tech in Python
  • Supports various LLM backends and benchmarks for evaluation
#agent#ai#cmu#distillation#georgia-tech#llm#llm-agent#ml#multi-agent-systems#nlp
Open on GitHub →

New repositories every 30 minutes

REDDYX AI scans GitHub 24/7 and ships the best AI/ML/Web3 projects to Telegram.

Join on Telegram
← Full catalog·Full index

// SIMILAR REPOSITORIES

SNIP - TOKEN SAVINGS UP TO 90%★ 280SAGENTS: AI Agents in Elixir★ 280VISUAL PRIMITIVES FOR AI THINKING★ 280RESEARCHCLAWBENCH - IMPROVING AI RESEARCH EFFECTIVENESS★ 280SECURITYCLAW AUTONOMOUS SOC AGENT★ 280phi - Simple Phi-4 Launch★ 280

← FULL CATALOG

AIFrontierLab/AgentArk — Agentark: One LLM Instead OF Many…