paper-with-me

홈 › Papers

Instruction Bleed: Cross-Module Interference in Prompt-Composed Agentic Systems

2026-06-24 · Ching-Yu Lin, Yifan Liu arxiv

Practitioners of prompt-composed agentic systems report a recurring failure mode: editing one prompt module silently shifts the behavior of others despite no shared variable or executable dependency. We formalize this as compositional behavioral leakage (CBL): interference between modules sharing a context window. CBL is enabled by architectural non-isolation: transformer self-attention provides no formal boundary between concatenated modules. We probe CBL on a deployed job-evaluation agent (Claude Sonnet 4.6, 144 trials) through a reusable three-channel protocol that perturbs non-focal modules along volume, content, and form. Only the content channel produces a detectable paired effect (Cohen's d = 0.63, bootstrap 95% CI excluding zero); no recommendation flipped -- a sub-threshold regime invisible to standard QA but compounding across the thousands of decisions a deployed agent makes. CBL is orthogonal to known agent-failure axes (adversarial injection, cognitive degradation, multi-agent fault propagation, privacy leakage). We contribute an operational definition, a reusable protocol, a falsifiable prediction set, and a system-class characterization, establishing cross-module interference measurement as a requirement for prompt-composed agent evaluation.

📄 PDF Abstract BibTeX arXiv:2606.26356

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Isolated Diffusion: Optimizing Multi-Concept Text-to-Image Generation Training-Freely with Isolated Diffusion Guidance

2024-03-25 · Jingyuan Zhu, Huimin Ma, Jiansheng Chen, Jian Yuan

Large-scale text-to-image diffusion models have achieved great success in synthesizing high-quality and diverse images given target text prompts. Despite the revolutionary image generation ability, current state-of-the-a…

Image Generationobject-detectionObject DetectionText to Image Generation+1

Synergistic Bleeding Region and Point Detection in Surgical Videos

2025-03-28 · Jialun Pei, Zhangjun Zhou, Diandian Guo, Zhixi Li 외

Intraoperative bleeding in laparoscopic surgery causes rapid obscuration of the operative field to hinder the surgical process. Intelligent detection of bleeding regions can quantify the blood loss to assist decision-mak…

Optical Flow Estimation

CollectionLoRA: Collecting 50 Effects in 1 LoRA via Multi-Teacher On-Policy Distillation

2026-05-25 · Fangtai Wu, Hailong Guo, Shijie Huang, Jiayi Song 외 arxiv

Customized image editing aims to equip pre-trained diffusion models with specific visual effects using limited paired data, typically via Low-Rank Adaptation (LoRA). As the number of desired effects grows, storing and dy…

Image Editing

Divide and Conquer: Grounding a Bleeding Areas in Gastrointestinal Image with Two-Stage Model

2024-12-21 · Yu-Fan Lin, Bo-Cheng Qiu, Chia-Ming Lee, Chih-Chung Hsu

Accurate detection and segmentation of gastrointestinal bleeding are critical for diagnosing diseases such as peptic ulcers and colorectal cancer. This study proposes a two-stage framework that decouples classification a…

Medical Image AnalysisMulti-Task LearningSegmentation

WikiTableEdit: A Benchmark for Table Editing by Natural Language Instruction

2024-03-05 · Zheng Li, Xiang Chen, Xiaojun Wan

Tabular data, as a crucial form of data representation, exists in diverse formats on the Web. When confronted with complex and irregular tables, manual modification becomes a laborious task. This paper investigates the p…