paper-with-me

홈 › Papers

Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems

2026-06-12 · Tan Zhu, Tong Yao, Kananart Kuwaranancharoen, Amit Singh, Yushang Lai, Deepa Mohan, Shankara Bhargava arxiv

Context adaptation automates prompt engineering in LLM-based systems by iteratively revising tunable prompts from task feedback, without modifying model weights. Extending this paradigm to multi-LLM agentic systems is crucial: existing methods suffer from inaccurate credit assignment and lack convergence guarantees. We propose \textbf{G}raph-based \textbf{T}arget \textbf{B}ack-\textbf{P}ropagation (GTBP), a context adaptation framework for agentic workflows modeled as directed acyclic graphs. GTBP propagates local target outputs backward through the workflow graph and uses target--output discrepancies to guide a stage-wise prompt update mechanism. Theoretically, we show that GTBP's stage-wise prompt updates become stable over iterations, and that a sufficiently capable LLM optimizer can decrease the overall objective. Empirically, GTBP consistently outperforms strong baselines across three benchmarks while maintaining comparable computational cost.

📄 PDF Abstract BibTeX arXiv:2606.14155

Code (0)

등록된 구현이 없습니다.

Tasks

Prompt Engineering

Similar Papers 제목 키워드 기반

Rethinking Propagation for Unsupervised Graph Domain Adaptation

2024-02-08 · Meihan Liu, Zeyu Fang, Zhen Zhang, Ming Gu 외

Unsupervised Graph Domain Adaptation (UGDA) aims to transfer knowledge from a labelled source graph to an unlabelled target graph in order to address the distribution shifts between graph domains. Previous works have pri…

Domain AdaptationGRAPH DOMAIN ADAPTATION

Semantic-Aware Temporal Adaptation for UAV Anti-UAV Tracking

2026-07-29 · Xiaozhen Qiao, Da Zhang, Yubin Guo, Junyu Gao 외 arxiv

UAV Anti-UAV tracking is an emerging low-altitude security task for localizing an adversarial UAV using the onboard camera of a moving observer UAV. It differs from conventional UAV tracking and ground-based Anti-UAV tra…

Object Tracking

Backpropagation-free Network for 3D Test-time Adaptation

2024-03-27 · CVPR 2024 1 · Yanshuo Wang, Ali Cheraghian, Zeeshan Hayder, Jie Hong 외

Real-world systems often encounter new data over time, which leads to experiencing target domain shifts. Existing Test-Time Adaptation (TTA) methods tend to apply computationally heavy and memory-intensive backpropagatio…

Test-time Adaptation

Few-shot Writer Adaptation via Multimodal In-Context Learning

2026-03-31 · Tom Simon, Stephane Nicolas, Pierrick Tranouez, Clement Chatelain 외 arxiv

While state-of-the-art Handwritten Text Recognition (HTR) models perform well on standard benchmarks, they frequently struggle with writers exhibiting highly specific styles that are underrepresented in the training data…

Handwritten Text Recognition

Efficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model

2024-12-24 · Yushu Li, Yongyi Su, Adam Goodge, Kui Jia 외

Vision-language models (VLMs) have revolutionized machine learning by leveraging large pre-trained models to tackle various downstream tasks. Despite improvements in label, training, and data efficiency, many state-of-th…

Language ModelingLanguage ModellingOut-of-Distribution Generalization