Graph-based Target Back-Propagation for Context Adaptation in Multi-LLM Agentic Systems
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Prompt EngineeringSimilar Papers 제목 키워드 기반
Rethinking Propagation for Unsupervised Graph Domain Adaptation
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 ADAPTATIONSemantic-Aware Temporal Adaptation for UAV Anti-UAV Tracking
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 TrackingBackpropagation-free Network for 3D Test-time Adaptation
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 AdaptationFew-shot Writer Adaptation via Multimodal In-Context Learning
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 RecognitionEfficient and Context-Aware Label Propagation for Zero-/Few-Shot Training-Free Adaptation of Vision-Language Model
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