AgentGrad: Intervention-guided Prompt Optimization for Multi Agent Systems

arXiv:2609.08572 · cs.AI · Submitted 2026-09-08 · Read on arXiv

cs.AI

Submitted: 2026-09-08

Updated: 2026-09-29

Comments: 13 pages

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Abstraction — 2× in this paper · explained in 1 episode
• Aggregation — 2× in this paper · explained in 1 episode
• Failure Modes — 2× in this paper · explained in 3 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 1× in this paper · explained in 3 episodes

Sources

• TextGrad: Automatic "Differentiation" via Text
• Modular Prompt Optimization: Optimizing Structured Prompts with Section-Local Textual Gradients
• Introducing MAPO: Momentum-Aided Gradient Descent Prompt Optimization
• From Flat Logs to Causal Graphs: Hierarchical Failure Attribution for LLM-based Multi-Agent Systems
• Rethinking Failure Attribution in Multi-Agent Systems: A Multi-Perspective Benchmark and Evaluation
• Learning from Contrastive Prompts: Automated Optimization and Adaptation
• Prompt Optimization with Human Feedback
• Qwen3 Technical Report
• A Tutorial on Bayesian Optimization
• CORRECT: COndensed eRror RECognition via knowledge Transfer in multi-agent systems
• Instruction-Following Evaluation for Large Language Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems