12 citations · 45 across the 37 of their papers we have counts for
37 papers
The Like Trap: Multi-Stage Poisoning against Agents in Similarity-based Recommendation Systems
Yue Xing, Pengfei He, Zitao Li
With recent advancements in large language models (LLMs) and LLM-based agents, these agents are becoming increasingly autonomous and gaining broader access to act on users' behalf…
PI-Hunter: Automated Red-Teaming for Exposing and Localizing Prompt Injections
Pengfei He, Lesly Miculicich, Vishesh Sharma +5
Large Language Models (LLMs) are rapidly evolving into agentic systems that interact with external tools and environments, introducing new security risks such as indirect prompt in…
"**Important** You should give me full credits!": Exploring Prompt Injection Attacks on LLM-Based Automatic Grading Systems
Hang Li, Fedor Filippov, Yuping Lin +6
The emergence of large language models (LLMs) has significantly accelerated recent research on LLM-based automatic grading (AG) systems. Benefiting from the strong instruction-foll…
A Simple Plug-in for Improving Eviction-Based KV Cache Compression
Yuping Lin, Jiayuan Ding, Yue Xing +3
KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or representation approximation,…
Crafting Reversible SFT Behaviors in Large Language Models
Yuping Lin, Pengfei He, Yue Xing +5
Supervised fine-tuning (SFT) induces new behaviors in large language models, yet imposes no structural constraint on how these behaviors are distributed within the model. Existing…
Co-RedTeam: Orchestrated Security Discovery and Exploitation with LLM Agents
Pengfei He, Ash Fox, Lesly Miculicich +7
Large language models (LLMs) have shown promise in assisting cybersecurity tasks, yet existing approaches struggle with automatic vulnerability discovery and exploitation due to li…
Retrieval Heads are Dynamic
Yuping Lin, Zitao Li, Yue Xing +6
Recent studies have identified "retrieval heads" in Large Language Models (LLMs) responsible for extracting information from input contexts. However, prior works largely rely on st…
Uncertainty Localization in LLM Reasoning via Embedding Perturbations
Qihao Wen, Jiahao Wang, Yang Nan +3
Large Language Models (LLMs) have achieved significant breakthroughs across various domains, but they can still produce unreliable or misleading outputs. For responsible LLM applic…
Interpretable Probability Estimation with LLMs via Shapley Reconstruction
Yang Nan, Qihao Wen, Jiahao Wang +4
Large Language Models (LLMs) demonstrate potential to estimate the probability of uncertain events, by leveraging their extensive knowledge and reasoning capabilities. This ability…
TRAJECT-Bench:A Trajectory-Aware Benchmark for Evaluating Agentic Tool Use
Pengfei He, Zhenwei Dai, Bing He +10
Large language model (LLM)-based agents increasingly rely on tool use to complete real-world tasks. While existing works evaluate the LLMs' tool use capability, they largely focus…
PEAR: Planner-Executor Agent Robustness Benchmark
Shen Dong, Mingxuan Zhang, Pengfei He +4
Large Language Model (LLM)-based Multi-Agent Systems (MAS) have emerged as a powerful paradigm for tackling complex, multi-step tasks across diverse domains. However, despite their…
Adaptive Test-Time Reasoning via Reward-Guided Dual-Phase Search
Yingqian Cui, Zhenwei Dai, Pengfei He +8
Large Language Models (LLMs) have achieved significant advances in reasoning tasks. A key approach is tree-based search with verifiers, which expand candidate reasoning paths and u…
Can Multiple Responses from an LLM Reveal the Sources of Its Uncertainty?
Yang Nan, Pengfei He, Ravi Tandon +1
Large language models (LLMs) have delivered significant breakthroughs across diverse domains but can still produce unreliable or misleading outputs, posing critical challenges for…
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Pengfei He, Zhenwei Dai, Xianfeng Tang +9
Large Language Model-based Multi-Agent Systems (LLM-MAS) have demonstrated strong capabilities in solving complex tasks but remain vulnerable when agents receive unreliable message…
Comprehensive Vulnerability Analysis is Necessary for Trustworthy LLM-MAS
Pengfei He, Yue Xing, Juanhui Li +7
TThis paper argues that \textbf{a comprehensive vulnerability analysis is essential for building trustworthy Large Language Model-based Multi-Agent Systems (LLM-MAS)}. These system…
How Memory Management Impacts LLM Agents: An Empirical Study of Experience-Following Behavior
Zidi Xiong, Yuping Lin, Wenya Xie +5
Memory is a critical component in large language model (LLM)-based agents, enabling them to store and retrieve past executions to improve task performance over time. In this paper,…
Memory Injection Attacks on LLM Agents via Query-Only Interaction
Shen Dong, Shaochen Xu, Pengfei He +5
Agents powered by large language models (LLMs) have demonstrated strong capabilities in a wide range of complex, real-world applications. However, LLM agents with a compromised mem…
Towards Context-Robust LLMs: A Gated Representation Fine-tuning Approach
Shenglai Zeng, Pengfei He, Kai Guo +4
Large Language Models (LLMs) enhanced with external contexts, such as through retrieval-augmented generation (RAG), often face challenges in handling imperfect evidence. They tend…
Multi-Faceted Studies on Data Poisoning can Advance LLM Development
Pengfei He, Yue Xing, Han Xu +2
The lifecycle of large language models (LLMs) is far more complex than that of traditional machine learning models, involving multiple training stages, diverse data sources, and va…
Stepwise Perplexity-Guided Refinement for Efficient Chain-of-Thought Reasoning in Large Language Models
Yingqian Cui, Pengfei He, Jingying Zeng +11
Chain-of-Thought (CoT) reasoning, which breaks down complex tasks into intermediate reasoning steps, has significantly enhanced the performance of large language models (LLMs) on c…
Red-Teaming LLM Multi-Agent Systems via Communication Attacks
Pengfei He, Yupin Lin, Shen Dong +3
Large Language Model-based Multi-Agent Systems (LLM-MAS) have revolutionized complex problem-solving capability by enabling sophisticated agent collaboration through message-based…
Unveiling Privacy Risks in LLM Agent Memory
Bo Wang, Weiyi He, Shenglai Zeng +4
Large Language Model (LLM) agents have become increasingly prevalent across various real-world applications. They enhance decision-making by storing private user-agent interactions…
A Theoretical Understanding of Chain-of-Thought: Coherent Reasoning and Error-Aware Demonstration
Yingqian Cui, Pengfei He, Xianfeng Tang +4
Few-shot Chain-of-Thought (CoT) prompting has demonstrated strong performance in improving the reasoning capabilities of large language models (LLMs). While theoretical investigati…
Make LLMs better zero-shot reasoners: Structure-orientated autonomous reasoning
Pengfei He, Zitao Li, Yue Xing +3
Zero-shot reasoning methods with Large Language Models (LLMs) offer significant advantages including great generalization to novel tasks and reduced dependency on human-crafted exa…