ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning

arXiv:2602.02192 · cs.LG, cs.DC · Submitted 2026-02-02 · Read on arXiv

cs.LG, cs.DC

Submitted: 2026-02-02

Updated: 2026-09-29

Terminology

• Reinforcement Learning — 2× in this paper · explained in 4 episodes
• GRPO — 1× in this paper · explained in 6 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Reinforcement Learning (RL) — 1× in this paper · explained in 25 episodes

Sources

• Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
• HARDMath: A Benchmark Dataset for Challenging Problems in Applied Mathematics
• AReaL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
• Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models
• DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
• AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training
• History Rhymes: Accelerating LLM Reinforcement Learning with RhymeRL
• Asynchronous RLHF: Faster and More Efficient Off-Policy RL for Language Models
• OpenAI GPT-5 System Card
• Proximal Policy Optimization Algorithms
• DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
• Laminar: A Scalable Asynchronous RL Post-Training Framework
• Scaling Laws for Collapse in Asynchronous GRPO
• Kimi k1.5: Scaling Reinforcement Learning with LLMs
• INTELLECT-2: A Reasoning Model Trained Through Globally Decentralized Reinforcement Learning
• Qwen3 Technical Report
• Parallax: Efficient LLM Inference Service over Decentralized Environment
• BAPO: Stabilizing Off-Policy Reinforcement Learning for LLMs via Balanced Policy Optimization with Adaptive Clipping
• Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms
• GAC: Stabilizing Asynchronous RL Training for LLMs via Gradient Alignment Control

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks