LGCLJun 12

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

arXiv:2606.14155v17.6h-index: 1
Predicted impact top 57% in LG · last 90 daysOriginality Incremental advance
AI Analysis

This work addresses the challenge of credit assignment and convergence in prompt optimization for multi-LLM workflows, offering a theoretically grounded and empirically superior solution.

GTBP introduces a graph-based back-propagation method for context adaptation in multi-LLM agentic systems, achieving consistent performance improvements over baselines across three benchmarks with comparable computational cost.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes