18 papers
Scivot: Benchmarking Principal-Investigator Judgment at Pivotal Moments of Scientific AutoResearch Agents
Youran Sun, Xingyu Ren, Chugang Yi +15
Large language model (LLM) agents can keep scientific experiments running for months with little human supervision, but reliable autonomous research also requires scientific judgme…
Zero2Repo: Can Coding Agents Build Repositories from Scratch?
Pei Yang, Tianyu Shi, Yuhang Yao +23
Coding agents are increasingly asked to build software rather than patch it, yet benchmarks for from-scratch repository construction are mostly limited to a single language and dep…
MERA: Model Evolution and Routing with Skill Adaptation for Agentic Systems at Scale
Yuhang Yao, Zeyu Wang, Wanyi Chen +8
LLM agents execute heterogeneous sequences of model calls within a single task: some invocations require careful reasoning, while others are structured steps such as formatting or…
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
Pei Yang, Wanyi Chen, Tongyun Yang +15
LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls.…
Combee: Scaling Prompt Learning for Self-Improving Language Model Agents
Hanchen Li, Runyuan He, Qizheng Zhang +11
Recent advances in prompt learning allow large language model agents to acquire task-relevant knowledge from inference-time context without parameter changes. For example, existing…
AOI: Turning Failed Trajectories into Training Signals for Autonomous Cloud Diagnosis
Pei Yang, Wanyi Chen, Asuka Yuxi Zheng +13
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…
Implicit Strategic Optimization: Rethinking Long-Horizon Decision-Making in Adversarial Poker Environments
Boyang Xia, Weiyou Tian, Qingnan Ren +7
Training large language model (LLM) agents for adversarial games is often driven by episodic objectives such as win rate. In long-horizon settings, however, payoffs are shaped by l…
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…
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…
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…
EVM-QuestBench: An Execution-Grounded Benchmark for Natural-Language Transaction Code Generation
Pei Yang, Wanyi Chen, Ke Wang +3
Large language models are increasingly applied to various development scenarios. However, in on-chain transaction scenarios, even a minor error can cause irreversible loss for user…
Speculative Decoding in Decentralized LLM Inference: Turning Communication Latency into Computation Throughput
Jingwei Song, Wanyi Chen, Xinyuan Song +7
Speculative decoding accelerates large language model (LLM) inference by using a lightweight draft model to propose tokens that are later verified by a stronger target model. While…
Multi-Agent Collaborative Reward Design for Enhancing Reasoning in Reinforcement Learning
Pei Yang, Ke Zhang, Ji Wang +5
We present CRM (Multi-Agent Collaborative Reward Model), a framework that replaces a single black-box reward model with a coordinated team of specialist evaluators to improve robus…
Lattica: A Decentralized Cross-NAT Communication Framework for Scalable AI Inference and Training
Ween Yang, Jason Liu, Suli Wang +4
The rapid expansion of distributed Artificial Intelligence (AI) workloads beyond centralized data centers creates a demand for new communication substrates. These substrates must o…
Parallax: Efficient LLM Inference Service over Decentralized Environment
Chris Tong, Youhe Jiang, Gufeng Chen +6
Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacent…
VeriLLM: A Lightweight Framework for Publicly Verifiable Decentralized Inference
Ke Wang, Zishuo Zhao, Xinyuan Song +7
Decentralized inference provides a scalable and resilient paradigm for serving large language models (LLMs), enabling fragmented global resource utilization and reducing reliance o…
Symphony: A Decentralized Multi-Agent Framework for Scalable Collective Intelligence
Ji Wang, Kashing Chen, Xinyuan Song +4
Most existing Large Language Model (LLM)-based agent frameworks rely on centralized orchestration, incurring high deployment costs, rigid communication topologies, and limited adap…
Echo: Decoupling Inference and Training for Large-Scale RL Alignment on Heterogeneous Swarms
Jie Xiao, Changyuan Fan, Qingnan Ren +6
Modern RL-based post-training for large language models (LLMs) co-locate trajectory sampling and policy optimisation on the same GPU cluster, forcing the system to switch between i…