18 papers
Tools Need Not Speak in Text: Latent Context Compression for Agents
Yuetong Liu, Zhehao Zhou, Yitong Zhang +2
Large language model (LLM) agents typically append raw tool outputs to their context. Over multi-step interactions, long and noisy observations incur substantial context overhead a…
CoACT: Action-Preserving Observation Compression for Coding Agents
Haorui Chen, Yuancheng Zhu, Yitong Zhang +1
LLM-based coding agents solve software-engineering tasks through iterative interactions with development environments, where returned observations accumulate in the context and bec…
Grammar-Constrained Decoding Can Jailbreak LLMs into Generating Malicious Code
Yitong Zhang, Shiteng Lu, Jia Li
Large Language Models (LLMs) are increasingly used for code generation, raising concerns that they may be misused to produce malicious code. Meanwhile, Grammar-Constrained Decoding…
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
Jinxiang Meng, Shaoping Huang, Fangyu Lei +17
Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from cod…
To See is Not to Master: Teaching LLMs to Use Private Libraries for Code Generation
Yitong Zhang, Chengze Li, Ruize Chen +4
Large Language Models (LLMs) have shown strong potential for code generation, yet they remain limited in private-library-oriented code generation, where the goal is to generate cod…
What Papers Don't Tell You: Recovering Tacit Knowledge for Automated Paper Reproduction
Lehui Li, Ruining Wang, Haochen Song +8
Automated paper reproduction -- generating executable code from academic papers -- is bottlenecked not by information retrieval but by the tacit knowledge that papers inevitably le…
PackMonitor: Enabling Zero Package Hallucinations Through Decoding-Time Monitoring
Xiting Liu, Yuetong Liu, Yitong Zhang +2
As Large Language Models (LLMs) are increasingly integrated into software development workflows, their trustworthiness has become a critical concern. However, in dependency recomme…
The Mask of Civility: Benchmarking Chinese Mock Politeness Comprehension in Large Language Models
Yitong Zhang, Yuhan Xiang, Mingxuan Liu
From a pragmatic perspective, this study systematically evaluates the differences in performance among representative large language models (LLMs) in recognizing politeness, impoli…
Improving Sampling for Masked Diffusion Models via Information Gain
Kaisen Yang, Jayden Teoh, Kaicheng Yang +2
Masked Diffusion Models (MDMs) enable flexible decoding orders, yet existing samplers remain largely greedy, selecting locally certain tokens without accounting for their downstrea…
Lookahead-then-Verify: Reliable Constrained Decoding for Diffusion LLMs under Context-Free Grammars
Yitong Zhang, Yongmin Li, Yuetong Liu +4
Diffusion Large Language Models (dLLMs) have demonstrated promising generative capabilities and are increasingly used to produce formal languages defined by context-free grammars,…
DAComp: Benchmarking Data Agents across the Full Data Intelligence Lifecycle
Fangyu Lei, Jinxiang Meng, Yiming Huang +14
Real-world enterprise data intelligence workflows encompass data engineering that turns raw sources into analytical-ready tables and data analysis that convert those tables into de…
Exploring the Potential of Diffusion Large Language Models in Code Generation
Chengze Li, Yitong Zhang, Jia Li +2
LLMs have become the mainstream approaches to code generation. Existing LLMs mainly employ autoregressive generation, i.e. generating code token-by-token from left to right. Howeve…
AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation
Liyi Cai, Yijie Ren, Yitong Zhang +1
Software automation has long been a central goal of software engineering, striving for software development that proceeds without human intervention. Recent efforts have leveraged…
DiffuTester: Accelerating Unit Test Generation for Diffusion LLMs via Mining Structural Pattern
Lekang Yang, Yuetong Liu, Yitong Zhang +1
Diffusion large language models (dLLMs) enable parallel generation and are promising for unit test generation (UTG), where efficient and large-scale automated testing is essential…
DiffuGuard: How Intrinsic Safety is Lost and Found in Diffusion Large Language Models
Zherui Li, Zheng Nie, Zhenhong Zhou +7
The rapid advancement of Diffusion Large Language Models (dLLMs) introduces unprecedented vulnerabilities that are fundamentally distinct from Autoregressive LLMs, stemming from th…
Environmental Injection Attacks against GUI Agents in Realistic Dynamic Environments
Yitong Zhang, Ximo Li, Liyi Cai +1
Graphical User Interface (GUI) agents are increasingly deployed to interact with online web services, yet their exposure to open-world content renders them vulnerable to Environmen…
DAVSP: Safety Alignment for Large Vision-Language Models via Deep Aligned Visual Safety Prompt
Yitong Zhang, Jia Li, Liyi Cai +1
Large Vision-Language Models (LVLMs) have achieved impressive progress across various applications but remain vulnerable to malicious queries that exploit the visual modality. Exis…
DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models
Yiming Huang, Jianwen Luo, Yan Yu +8
We introduce DA-Code, a code generation benchmark specifically designed to assess LLMs on agent-based data science tasks. This benchmark features three core elements: First, the ta…