11 papers
Breaking Planner Integrity Boundary: Enviroment State-Text Injection Attack on LLM-Driven Embodied Agents
Jiawei Liu, Jiacheng Guo, Tian Zhang +7
Large language model (LLM)-driven embodied agents rely on environment states to interpret scenes, generate high-level plans, and drive physical execution, making planner-visible st…
ProRetrieval: Learning to Orchestrate Hybrid Search via Executable Program Synthesis
Chengsong You, Zhen Sun, Yunhai Hu +17
Real-world retrieval often composes structured constraints with semantic intents over text and images through arbitrary Boolean logic. Existing hybrid pipelines such as reciprocal…
DocPC: Document-Level Visual Retrieval via Representative Page Composition
Chengsong You, Qiyi Jiang, Junwei Zhou +12
Visual document retrieval has advanced by encoding page screenshots with vision-language models, bypassing OCR pipelines. However, existing methods remain page-centric, misaligned…
Security of Foundation-Model-Powered Embodied Agents: Attack Surfaces, Attacks, Defenses, and Evaluation
Jiawei Liu, Jiacheng Guo, Tian Zhang +4
Foundation models are increasingly used for perception, reasoning, planning, and action generation in embodied agents, creating security risks that can propagate from digital input…
DSL-R1: From SQL to DSL for Training Retrieval Agents across Structured and Unstructured Data with Reinforcement Learning
Yunhai Hu, Junwei Zhou, Yumo Cao +8
Effective retrieval in complex domains requires bridging the gap between structured metadata and unstructured content. Existing systems typically isolate these capabilities, relyin…
AgentSentry: Mitigating Indirect Prompt Injection in LLM Agents via Temporal Causal Diagnostics and Context Purification
Tian Zhang, Yiwei Xu, Juan Wang +8
Tool-augmented large language model (LLM) agents aggregate dialogue history, tool outputs, and retrieved content into an accumulated runtime state to complete multi-step tasks. Thi…
FORESTLLM: Large Language Models Make Random Forest Great on Few-shot Tabular Learning
Zhihan Yang, Jiaqi Wei, Xiang Zhang +6
Tabular data high-stakes critical decision-making in domains such as finance, healthcare, and scientific discovery. Yet, learning effectively from tabular data in few-shot settings…
SlideGen: Collaborative Multimodal Agents for Scientific Slide Generation
Xin Liang, Zhilin Zhang, Xiang Zhang +4
Creating presentation slides from scientific papers is not simply a matter of summarizing paragraphs. A presenter is required to decide what story to tell, which figures and equati…
TimeSeriesScientist: A General-Purpose AI Agent for Time Series Analysis
Haokun Zhao, Xiang Zhang, Jiaqi Wei +4
Time series forecasting is central to decision-making in domains as diverse as energy, finance, climate, and public health. In practice, forecasters face thousands of short, noisy…
PosterGen: Aesthetic-Aware Multi-Modal Paper-to-Poster Generation via Multi-Agent LLMs
Zhilin Zhang, Xiang Zhang, Jiaqi Wei +2
Multi-agent systems built upon large language models (LLMs) have demonstrated remarkable capabilities in tackling complex compositional tasks. In this work, we apply this paradigm…
Tokenization Constraints in LLMs: A Study of Symbolic and Arithmetic Reasoning Limits
Xiang Zhang, Juntai Cao, Jiaqi Wei +2
Tokenization is the first - and often underappreciated - layer of computation in language models. While Chain-of-Thought (CoT) prompting enables transformer models to approximate r…