GRADE: Graph Representation of LLM Agent Dependency and Execution

arXiv:2606.22741 · cs.LG · Submitted 2026-06-22 · Read on arXiv

cs.LG

Submitted: 2026-06-22

Updated: 2026-09-12

Comments: 30 pages, 7 figures, 13 tables. Code: https://github.com/yzhao062/grade

Code: https://github.com/yzhao062/grade

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

Terminology

• Trace — 47× in this paper · explained in 2 episodes
• AUC — 33× in this paper · explained in 2 episodes
• Failure Modes — 7× in this paper · explained in 3 episodes
• Heterogeneous Graph — 5× in this paper · explained in 2 episodes
• Accuracy — 4× in this paper · explained in 1 episode
• Benchmark — 4× in this paper · explained in 2 episodes
• Multi-agent Collaboration — 4× in this paper · explained in 2 episodes
• Agentic System — 3× in this paper · explained in 2 episodes
• Pruning — 3× in this paper · explained in 4 episodes
• Abstraction — 2× in this paper · explained in 1 episode
• Redundancy — 2× in this paper · explained in 2 episodes
• Representation Learning — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Agentic Reasoning — 1× in this paper · explained in 1 episode
• Agentic Workflows — 1× in this paper · explained in 1 episode
• Foundation Model — 1× in this paper · explained in 3 episodes
• Foundation Models — 1× in this paper · explained in 7 episodes
• GNNs — 1× in this paper · explained in 2 episodes
• Generalization — 1× in this paper · explained in 13 episodes
• In International Conference on Learning Representations — 1× in this paper
• Linear probe — 1× in this paper · explained in 2 episodes
• Multi-agent Collaborative Framework — 1× in this paper · explained in 2 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Transformer — 1× in this paper · explained in 2 episodes
• Verifier — 1× in this paper · explained in 2 episodes

Sources

• $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
• Why Do Multi-Agent LLM Systems Fail?
• AgentOps: Enabling Observability of LLM Agents
• SentinelAgent: Graph-based Anomaly Detection in Multi-Agent Systems
• MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework
• Topology Matters: Measuring Memory Leakage in Multi-Agent LLMs
• AgentRewardBench: Evaluating Automatic Evaluations of Web Agent Trajectories
• The Rise and Potential of Large Language Model Based Agents: A Survey
• When Only the Final Text Survives: Implicit Execution Tracing for Multi-Agent Auditing
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• Training Software Engineering Agents and Verifiers with SWE-Gym
• $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
• From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents
• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
• G-Safeguard: A Topology-Guided Security Lens and Treatment on LLM-based Multi-agent Systems
• GNNs as Predictors of Agentic Workflow Performances
• OpenHands: An Open Platform for AI Software Developers as Generalist Agents
• GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: Local-Consistency Optimisation for Bayesian Neural Networks
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks