1 citations · 1 across the 7 of their papers we have counts for
8 papers
From Attack Success to Attack Severity: Counterfactual Memory Attacks on LLM Agents
Mingxi Zou, Langzhang Liang, Zhuo Wang +3
As LLM agents increasingly rely on persistent memory for long-horizon and personalized behavior, they can retain and reuse information across interactions, but this also creates a…
Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems
Yiyang Zhao, Zhuo Zhang, Qingxuan Le +2
The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluati…
EPIC-Bench: A Perception-Centric Benchmark for Fine-Grained Embodied Visual Grounding in Vision-Language Models
Haozhe Shan, Xiancong Ren, Han Dong +10
While large vision-language models (VLMs) are increasingly adopted as the perceptual backbone for embodied agents, their fundamental vision-language grounding (VLG) capability in e…
Remember the Decision, Not the Description: A Rate-Distortion Framework for Agent Memory
Mingxi Zou, Zhihan Guo, Langzhang Liang +6
Long-horizon language agents must operate under limited runtime memory, yet existing memory mechanisms often organize experience around descriptive criteria such as relevance, sali…
CoTEvol: Self-Evolving Chain-of-Thoughts for Data Synthesis in Mathematical Reasoning
Zhuo Wang, Zhuo Zhang, Yafu Li +3
Large Language Models (LLMs) exhibit strong mathematical reasoning when trained on high-quality Chain-of-Thought (CoT) that articulates intermediate steps, yet costly CoT curation…
Simple Yet Effective: Extracting Private Data Across Clients in Federated Fine-Tuning of Large Language Models
Yingqi Hu, Zhuo Zhang, Jingyuan Zhang +4
Federated large language models (FedLLMs) enable cross-silo collaborative training among institutions while preserving data locality, making them appealing for privacy-sensitive do…
Can we only use guideline instead of shot in prompt?
Jiaxiang Chen, Song Wang, Zhucong Li +4
Currently, prompting techniques can be mainly divided into two categories:1)shot method implicitly inspires the model to answer the question by mimicing the steps in the given exam…
PPFedIT: Towards Privacy-Preserving Federated Instruction Tuning with Few-shot Local Examples
Zhuo Zhang, Jingyuan Zhang, Jintao Huang +7
Instruction tuning aligns large language models (LLMs) with human intentions but requires diverse, high-quality data that are difficult to collect in privacy-sensitive domains. Fed…