30 citations · 33 across the 14 of their papers we have counts for
15 papers
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…
VISTA: An End-to-End Benchmark for Visual Spec-to-Web-App Coding Agents
JunJia Guo, Yuhang Yao, Jiawei +4
Coding agents can now build applications from design mockups, but a screen that looks right is not an application that works. Existing benchmarks either score visual reconstruction…
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.…
Harnessing AtomisticSkills for Agentic Atomistic Research
Bowen Deng, Bohan Li, Matthew Cox +20
Computational materials science and chemistry span vast knowledge domains and fractured software ecosystems. Although large language models (LLMs) have demonstrated research capabi…
D-PACE: Dynamic Position-Aware Cross-Entropy for Parallel Speculative Drafting
Tianyu Wu, Yu Yao, Zhenting Qi +7
Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters su…
GAP: Graph-Based Agent Planning with Parallel Tool Use and Reinforcement Learning
Jiaqi Wu, Qinlao Zhao, Zefeng Chen +4
Autonomous agents powered by large language models (LLMs) have shown impressive capabilities in tool manipulation for complex task-solving. However, existing paradigms such as ReAc…
Toward Super Agent System with Hybrid AI Routers
Yuhang Yao, Haixin Wang, Yibo Chen +5
AI Agents powered by Large Language Models are transforming the world through enormous applications. A super agent has the potential to fulfill diverse user needs, such as summariz…
Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs
Yide Ran, Zhaozhuo Xu, Yuhang Yao +9
The rapid advancement of Large Language Models (LLMs) has led to their increased integration into mobile devices for personalized assistance, which enables LLMs to call external AP…
ScaleLLM: A Resource-Frugal LLM Serving Framework by Optimizing End-to-End Efficiency
Yuhang Yao, Han Jin, Alay Dilipbhai Shah +7
Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience…
TensorOpera Router: A Multi-Model Router for Efficient LLM Inference
Dimitris Stripelis, Zijian Hu, Jipeng Zhang +6
With the rapid growth of Large Language Models (LLMs) across various domains, numerous new LLMs have emerged, each possessing domain-specific expertise. This proliferation has high…
TorchOpera: A Compound AI System for LLM Safety
Shanshan Han, Zijian Hu, Alay Dilipbhai Shah +5
We introduce TorchOpera, a compound AI system for enhancing the safety and quality of prompts and responses for Large Language Models. TorchOpera ensures that all user prompts are…
LLM Multi-Agent Systems: Challenges and Open Problems
Shanshan Han, Qifan Zhang, Weizhao Jin +1
This paper explores multi-agent systems and identify challenges that remain inadequately addressed. By leveraging the diverse capabilities and roles of individual agents, multi-age…
Kick Bad Guys Out! Conditionally Activated Anomaly Detection in Federated Learning with Zero-Knowledge Proof Verification
Shanshan Han, Wenxuan Wu, Baturalp Buyukates +4
Federated Learning (FL) systems are susceptible to adversarial attacks, such as model poisoning attacks and backdoor attacks. Existing defense mechanisms face critical limitations…
FedSecurity: Benchmarking Attacks and Defenses in Federated Learning and Federated LLMs
Shanshan Han, Baturalp Buyukates, Zijian Hu +13
This paper introduces FedSecurity, an end-to-end benchmark that serves as a supplementary component of the FedML library for simulating adversarial attacks and corresponding defens…