6 papers
AgentPolicyForge: From Executable Environments to Policy Benchmarks and Adaptive Guards
Chao Shang, Wanyu Du, Yi Zhang +1
Customized agent deployments define policies over tools, resources, and execution conditions. Providing these policies in the task agent's prompt does not reliably prevent violatio…
PerMIT: Securing Persistent Memory for LLM Agents via Machine-Checked Integrity Theorems and Scalable Community Trust
Tanqiu Jiang, Min Bai, Sadat Shahriar +2
Persistent memory is a largely undefended surface for injection and poisoning, and the same risk limits memory sharing among agents. We present PerMIT, a memory architecture with p…
The Subtle Art of Defection: Understanding Uncooperative Behaviors in LLM based Multi-Agent Systems
Devang Kulshreshtha, Wanyu Du, Raghav Jain +4
This paper introduces a novel framework for simulating and analyzing how uncooperative behaviors can destabilize or collapse LLM-based multi-agent systems. Our framework includes t…
Peacemaker or Troublemaker: How Sycophancy Shapes Multi-Agent Debate
Binwei Yao, Chao Shang, Wanyu Du +6
Large language models (LLMs) often display sycophancy, a tendency toward excessive agreeability. This behavior poses significant challenges for multi-agent debating systems (MADS)…
Towards Improved Preference Optimization Pipeline: from Data Generation to Budget-Controlled Regularization
Zhuotong Chen, Fang Liu, Jennifer Zhu +2
Direct Preference Optimization (DPO) and its variants have become the de facto standards for aligning large language models (LLMs) with human preferences or specific goals. However…
DFlow: Diverse Dialogue Flow Simulation with Large Language Models
Wanyu Du, Song Feng, James Gung +4
Developing language model-based dialogue agents requires effective data to train models that can follow specific task logic. However, most existing data simulation methods focus on…