9 papers
AgentOrchestra: Orchestrating Multi-Agent Intelligence with the Tool-Environment-Agent(TEA) Protocol
Wentao Zhang, Liang Zeng, Yuzhen Xiao +7
Recent advances in LLM-based agent systems have shown promise on complex, long-horizon tasks, but existing agent protocols (e.g., A2A and MCP) do not adequately support lifecycle-a…
How LLMs Are Persuaded: A Few Attention Heads, Rerouted
Xiangkun Sun, Lingkai Kong, Aoqi Zhang +2
Language models can be persuaded to abandon factual knowledge. This vulnerability is central to AI safety, but its internal mechanism remains poorly understood. We uncover a compac…
LLM Advertisement based on Neuron Auctions
Peiran Yun, Wenxin Xu, Jiayuan Liu +4
As Large Language Models (LLMs) transition into conversational agents, generative advertising emerges as a crucial monetization strategy. However, embedding advertisements within u…
Skywork-Reward-V2: Scaling Preference Data Curation via Human-AI Synergy
Chris Yuhao Liu, Liang Zeng, Yuzhen Xiao +9
Despite the critical role of reward models (RMs) in Reinforcement Learning from Human Feedback (RLHF), current state-of-the-art open RMs perform poorly on most existing evaluation…
Translate Policy to Language: Flow Matching Generated Rewards for LLM Explanations
Xinyi Yang, Liang Zeng, Heng Dong +6
As humans increasingly share environments with diverse agents powered by RL, LLMs, and beyond, the ability to explain agent policies in natural language is vital for reliable coexi…
Skywork-SWE: Unveiling Data Scaling Laws for Software Engineering in LLMs
Liang Zeng, Yongcong Li, Yuzhen Xiao +8
Software engineering (SWE) has recently emerged as a crucial testbed for next-generation LLM agents, demanding inherent capabilities in two critical dimensions: sustained iterative…