6 papers
GTA-2: Benchmarking General Tool Agents from Atomic Tool-Use to Open-Ended Workflows
Jize Wang, Xuanxuan Liu, Yining Li +7
The development of general-purpose agents requires a shift from executing simple instructions to completing complex, real-world productivity workflows. However, current tool-use be…
RouteMoA: Dynamic Routing without Pre-Inference Boosts Efficient Mixture-of-Agents
Jize Wang, Han Wu, Zhiyuan You +9
Mixture-of-Agents (MoA) improves LLM performance through layered collaboration, but its dense topology raises costs and latency. Existing methods employ LLM judges to filter respon…
Partial Feedback Online Learning
Shihao Shao, Cong Fang, Zhouchen Lin +1
We study a new learning protocol, termed partial-feedback online learning, where each instance admits a set of acceptable labels, but the learner observes only one acceptable label…
Binding Agent ID: Unleashing the Power of AI Agents with accountability and credibility
Zibin Lin, Shengli Zhang, Guofu Liao +2
Autonomous AI agents lack traceable accountability mechanisms, creating a fundamental dilemma where systems must either operate as ``downgraded tools'' or risk real-world abuse. Th…
EmbedGrad: Gradient-Based Prompt Optimization in Embedding Space for Large Language Models
Xiaoming Hou, Jiquan Zhang, Zibin Lin +2
Effectively adapting powerful pretrained foundation models to diverse tasks remains a key challenge in AI deployment. Current approaches primarily follow two paradigms:discrete opt…
VeriLoRA: Fine-Tuning Large Language Models with Verifiable Security via Zero-Knowledge Proofs
Guofu Liao, Taotao Wang, Shengli Zhang +3
Fine-tuning large language models (LLMs) is crucial for adapting them to specific tasks, yet it remains computationally demanding and raises concerns about correctness and privacy,…