12 papers
Staleness-Learning Rate Scaling Laws for Asynchronous RLHF
Jingwei Song, Haofeng Xu, Jie Xiao +8
High-throughput RLHF systems often decouple rollout generation from policy optimization, leading to the use of stale rollouts during learner updates. In this work, we study the eff…
Symphony-Coord: Adaptive Routing for Multi-Agent LLM Systems
Zhaoyang Guan, Huixi Cao, Ming Zhong +6
Multi-agent large language model systems can tackle complex multi-step tasks by decomposing work and coordinating specialized behaviors. However, current coordination mechanisms ty…
ECHO-2: A Large-Scale Distributed Rollout Framework for Cost-Efficient Reinforcement Learning
Jingwei Song, Meng Chen, Jie Xiao +15
Reinforcement learning (RL) is a critical stage in post-training large language models (LLMs), involving repeated interaction between rollout generation, reward evaluation, and cen…
Hide-and-Shill: A Reinforcement Learning Framework for Market Manipulation Detection in Symphony-a Decentralized Multi-Agent System
Ronghua Shi, Yiou Liu, Yuchun Feng +3
Decentralized finance (DeFi) has introduced a new era of permissionless financial innovation but also led to unprecedented market manipulation. Without centralized oversight, malic…
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification
Jingwei Song, Xinyu Wang, Hanbin Wang +6
Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by t…
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
Pei Yang, Wanyi Chen, Asuka Yuxi Zheng +11
Large language model (LLM) agents offer a promising data-driven approach to automating Site Reliability Engineering (SRE), yet their enterprise deployment is constrained by three c…