The first SoK on LLM-based AutoPT frameworks provides a six-dimension taxonomy of agent designs and a unified empirical benchmark evaluating 15 frameworks via over 10 billion tokens and 1,500 manually reviewed logs.
hub Canonical reference
Why Do Multi-Agent LLM Systems Fail?
Canonical reference. 92% of citing Pith papers cite this work as background.
68
Pith papers citing it
Background
92% of classified citations
abstract
Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understanding of why MAS fail. Addressing this question requires systematic identification and analysis of failure patterns. We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks. MAST-Data is the first multi-agent system dataset to outline the failure dynamics in MAS for guiding the development of better future systems. To enable systematic classification of failures for MAST-Data, we build the first Multi-Agent System Failure Taxonomy (MAST). We develop MAST through rigorous analysis of 150 traces, guided closely by expert human annotators and validated by high inter-annotator agreement (kappa = 0.88). This process identifies 14 unique modes, clustered into 3 categories: (i) system design issues, (ii) inter-agent misalignment, and (iii) task verification. To enable scalable annotation, we develop an LLM-as-a-Judge pipeline with high agreement with human annotations. We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent), demonstrating improvement headrooms from better MAS design. Our analysis provides insights revealing that identified failures require more sophisticated solutions, highlighting a clear roadmap for future research. We publicly release our comprehensive dataset (MAST-Data), the MAST, and our LLM annotator to facilitate widespread research and development in MAS.
hub tools
citation-role summary
background 25
citation-polarity summary
claims ledger
- abstract Despite enthusiasm for Multi-Agent LLM Systems (MAS), their performance gains on popular benchmarks are often minimal. This gap highlights a critical need for a principled understanding of why MAS fail. Addressing this question requires systematic identification and analysis of failure patterns. We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks. MAST-Data is the first multi-agent system dataset to outline the failure dynamics in MAS for guiding the development of better future systems. To enable systematic classification of fail
co-cited works
roles
background 23representative citing papers
Proposes EpG and OOI metrics showing agentic workflows use 4.33x more energy per successful goal than linear baselines due to orchestration structure.
Introduces the stochastic-deterministic boundary (SDB) as a load-bearing primitive for LLM agent runtimes and provides a five-step methodology plus catalog of six patterns adapted from distributed systems.
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
AstraFlow decouples RL components into autonomous dataflow services to natively support multi-policy agentic LLM training, elastic scaling, and cross-region execution with 2.7x speedup on math, code, search, and AgentBench workloads.
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
A span-decomposed evaluation framework for AI agents achieves state-of-the-art results on GAIA and SWE-Bench with up to 3.5x gains in localization accuracy by breaking traces into independent per-span judgments.
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
TraceFix repairs LLM-generated multi-agent protocols via TLA+ counterexamples to achieve full verification on all tested tasks and higher completion rates than prompt-only baselines.
Enforcing role separation in agent teams reveals that prompt-only setups hide coordination failures, with verifiers approving 49% of failing work and teams sometimes harming performance when solo agents already succeed.
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
TraceToChain models LLM agent traces as absorbing DTMCs using automatic clustering and smoothed MLE, with KS and AIC validation, to reconcile pass@k, pass^k, and RDC as projections of a single first-passage success-time distribution.
AgentEval evaluates agentic workflows via DAGs with step metrics, a 21-category failure taxonomy, and error propagation tracking, yielding 2.17x higher failure recall than end-to-end methods and strong human agreement.
HANDRAISER learns optimal interruption points in multi-agent LLM communication using estimated future reward and cost, achieving 32.2% lower communication cost with comparable or better task results across games, scheduling, and debate.
GraphBit is a DAG-based engine-orchestrated framework for agentic LLMs that achieves 67.6% accuracy with zero hallucinations on GAIA benchmarks.
FORGE enforces security policies in agentic systems via Datalog over abstract predicates with an observability service and reference monitor that guarantees policy semantics when the environment contract holds.
A large-scale empirical study categorizes bugs in LLM agents and demonstrates that a specialized LLM agent can annotate them accurately at very low cost.
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
Stage-Audit raises source-frontier precision from 0.356 to 0.505 and F1 from 0.334 to 0.451 on a 51-instance cross-domain set by enforcing disjoint write rights and row-level source gates.
VerifyMAS improves failure attribution in LLM multi-agent systems via hypothesis verification on full trajectories, error taxonomy-based data construction, and fine-tuned verifier models, outperforming prior direct-prediction methods on Aegis-Bench and Who&When.
ACT*ONOMY is a Grounded-Theory-derived hierarchical taxonomy and open repository that enables systematic comparison and characterization of autonomous agent behavior across trajectories.
citing papers explorer
-
Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing
The first SoK on LLM-based AutoPT frameworks provides a six-dimension taxonomy of agent designs and a unified empirical benchmark evaluating 15 frameworks via over 10 billion tokens and 1,500 manually reviewed logs.
-
Energy per Successful Goal: Goal-Level Energy Accounting for Agentic AI Systems
Proposes EpG and OOI metrics showing agentic workflows use 4.33x more energy per successful goal than linear baselines due to orchestration structure.
-
A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
Introduces the stochastic-deterministic boundary (SDB) as a load-bearing primitive for LLM agent runtimes and provides a five-step methodology plus catalog of six patterns adapted from distributed systems.
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs
AstraFlow decouples RL components into autonomous dataflow services to natively support multi-policy agentic LLM training, elastic scaling, and cross-region execution with 2.7x speedup on math, code, search, and AgentBench workloads.
-
Beyond Individual Intelligence: Surveying Collaboration, Failure Attribution, and Self-Evolution in LLM-based Multi-Agent Systems
A survey that unifies prior work on multi-agent LLM systems via the LIFE framework, mapping dependencies across collaboration, failure attribution, and autonomous self-evolution while identifying cross-stage challenges.
-
Holistic Evaluation and Failure Diagnosis of AI Agents
A span-decomposed evaluation framework for AI agents achieves state-of-the-art results on GAIA and SWE-Bench with up to 3.5x gains in localization accuracy by breaking traces into independent per-span judgments.
-
AgentForesight: Online Auditing for Early Failure Prediction in Multi-Agent Systems
AgentForesight introduces an online auditor model that predicts decisive errors in multi-agent trajectories at the earliest step using a coarse-to-fine reinforcement learning recipe on a new curated dataset AFTraj-2K.
-
TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples
TraceFix repairs LLM-generated multi-agent protocols via TLA+ counterexamples to achieve full verification on all tested tasks and higher completion rates than prompt-only baselines.
-
TeamBench: Evaluating Agent Coordination under Enforced Role Separation
Enforcing role separation in agent teams reveals that prompt-only setups hide coordination failures, with verifiers approving 49% of failing work and teams sometimes harming performance when solo agents already succeed.
-
Improving the Efficiency of Language Agent Teams with Adaptive Task Graphs
LATTE coordinates LLM agent teams with an evolving shared task graph, cutting token use, time, and failures while matching or beating accuracy of MetaGPT, leader-worker, and static methods.
-
Inference-Time Budget Control for LLM Search Agents
A VOI-based controller for dual inference budgets improves multi-hop QA performance by prioritizing search actions and selectively finalizing answers.
-
Measuring the Unmeasurable: Markov Chain Reliability for LLM Agents
TraceToChain models LLM agent traces as absorbing DTMCs using automatic clustering and smoothed MLE, with KS and AIC validation, to reconcile pass@k, pass^k, and RDC as projections of a single first-passage success-time distribution.
-
AgentEval: DAG-Structured Step-Level Evaluation for Agentic Workflows with Error Propagation Tracking
AgentEval evaluates agentic workflows via DAGs with step metrics, a 21-category failure taxonomy, and error propagation tracking, yielding 2.17x higher failure recall than end-to-end methods and strong human agreement.
-
Learning to Interrupt in Language-based Multi-agent Communication
HANDRAISER learns optimal interruption points in multi-agent LLM communication using estimated future reward and cost, achieving 32.2% lower communication cost with comparable or better task results across games, scheduling, and debate.
-
GraphBit: A Graph-based Agentic Framework for Non-Linear Agent Orchestration
GraphBit is a DAG-based engine-orchestrated framework for agentic LLMs that achieves 67.6% accuracy with zero hallucinations on GAIA benchmarks.
-
Formal Policy Enforcement for Real-World Agentic Systems
FORGE enforces security policies in agentic systems via Datalog over abstract predicates with an observability service and reference monitor that guarantees policy semantics when the environment contract holds.
-
When Agents Fail: A Comprehensive Study of Bugs in LLM Agents with Automated Labeling
A large-scale empirical study categorizes bugs in LLM agents and demonstrates that a specialized LLM agent can annotate them accurately at very low cost.
-
When Identity Skews Debate: Anonymization for Bias-Reduced Multi-Agent Reasoning
Anonymization in multi-agent debate reduces identity bias by equalizing self and peer weights in a Bayesian update model, quantified by the Identity Bias Coefficient.
-
When Planning Fails Despite Correct Execution: On Epistemic Calibration for LLM-Based Multi-Agent Systems
Introduces EPC-AW to mitigate epistemic miscalibration in LLM multi-agent planning via consistency-based selection and refinement, reporting 9.75% average success improvement.
-
Self-Evolving Multi-Agent Systems via Decentralized Memory
DecentMem is a decentralized dual-pool memory framework for self-evolving multi-agent systems that provides O(log T) regret guarantees and yields up to 23.8% accuracy gains over centralized baselines.
-
Stage-Audit: Auditable Source-Frontier Discovery for Cross-Wiki Tables
Stage-Audit raises source-frontier precision from 0.356 to 0.505 and F1 from 0.334 to 0.451 on a 51-instance cross-domain set by enforcing disjoint write rights and row-level source gates.
-
VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems
VerifyMAS improves failure attribution in LLM multi-agent systems via hypothesis verification on full trajectories, error taxonomy-based data construction, and fine-tuned verifier models, outperforming prior direct-prediction methods on Aegis-Bench and Who&When.
-
How to Interpret Agent Behavior
ACT*ONOMY is a Grounded-Theory-derived hierarchical taxonomy and open repository that enables systematic comparison and characterization of autonomous agent behavior across trajectories.
-
SWE-Cycle: Benchmarking Code Agents across the Complete Issue Resolution Cycle
SWE-Cycle benchmark shows sharp drops in code agent success rates from isolated tasks to full autonomous issue resolution, highlighting cross-phase dependency issues.
-
Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy
Base LLMs show multi-agent yield to peer pressure at rates equal to or higher than aligned models, localized by activation patching to mid-layers where attention dominates, with one dissenter cutting yield by 54-73 points while prompt defenses fail on variants.
-
PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
PIVOT refines LLM agent trajectories through plan-inspect-evolve-verify stages using environment feedback, yielding up to 94% relative gains in constraint satisfaction and 3-5x token efficiency over prior refinement methods.
-
Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems
Coordination treated as a separable architectural layer in LLM multi-agent systems yields distinguishable Murphy-decomposed performance signatures on prediction-market tasks, with some configurations dominating a cost-quality Pareto frontier.
-
TeamTR: Trust-Region Fine-Tuning for Multi-Agent LLM Coordination
TeamTR is a trust-region framework for multi-agent LLM fine-tuning that resamples trajectories after each update to convert quadratic compounding occupancy shift into linear scaling and yields per-update improvement lower bounds.
-
Trace-Level Analysis of Information Contamination in Multi-Agent Systems
Agent workflows can diverge substantially from contaminated inputs yet recover correct answers, or stay similar while failing, as measured by trace divergence on GAIA tasks.
-
EPM-RL: Reinforcement Learning for On-Premise Product Mapping in E-Commerce
EPM-RL uses PEFT followed by RL with agent-based rewards from judge models to create a trainable in-house product mapping model that improves on fine-tuning alone and beats API baselines in quality-cost while enabling private use.
-
VLAA-GUI: Knowing When to Stop, Recover, and Search, A Modular Framework for GUI Automation
VLAA-GUI adds mandatory visual verifiers, multi-tier loop breakers, and on-demand search to GUI agents, reaching 77.5% on OSWorld and 61.0% on WindowsAgentArena with some models exceeding human performance.
-
Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots
A new benchmark shows LLM smartphone agents achieve comparable success with screen text alone as with screenshots, but both fail often due to UI accessibility and reasoning gaps.
-
Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks
Token-level contrastive attribution yields informative signals for some LLM benchmark failures but is not universally applicable across datasets and models.
-
Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems
LLM agent societies develop power-law coordination cascades and intellectual elites through an integration bottleneck that grows with system size.
-
Semantic Consensus: Process-Aware Conflict Detection and Resolution for Enterprise Multi-Agent LLM Systems
Semantic Consensus Framework achieves 100% workflow completion in multi-agent LLM setups by detecting and resolving semantic conflicts, far outperforming existing approaches at 25.1%.
-
Security Considerations for Multi-agent Systems
No existing AI security framework covers a majority of the 193 identified multi-agent system threats in any category, with OWASP Agentic Security Initiative achieving the highest overall coverage at 65.3%.
-
Characterizing Faults in Agentic AI: A Taxonomy of Types, Symptoms, and Root Causes
An empirical study of real-world issues yields a taxonomy of 34 fault types, symptoms, and root causes in agentic AI systems, validated by 145 practitioners.
-
Process-Centric Analysis of Agentic Software Systems
Graphectory turns stochastic agent trajectories into analyzable graphs, showing that stronger models and successful fixes follow coherent localization-validation steps while failures are chaotic, and online detection plus rollback improves resolution rates by 6.9-23.5%.
-
GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis
GenoMAS deploys six specialized LLM agents with guided planning to preprocess transcriptomic data and identify genes, reaching 89.13% composite similarity and 60.48% F1 on the GenoTEX benchmark while outperforming prior methods.
-
Compiling Agentic Workflows into LLM Weights: Near-Frontier Quality at Two Orders of Magnitude Less Cost
Compiling agentic workflows into LLM weights creates subterranean agents with near-frontier quality at two orders of magnitude less cost, validated empirically on travel booking, Zoom support, and insurance claims tasks.
-
Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks
Pramana defines a typed ClaimAttestation protocol with four variants and verify operations, specifies its lifecycle in TLA+, model-checks it with TLC, and provides a tested Python implementation for auditable agent claims.
-
Position: A Three-Layer Probabilistic Assume-Guarantee Architecture Is Structurally Required for Safe LLM Agent Deployment
A three-layer probabilistic assume-guarantee architecture is structurally required for safe LLM agent deployment.
-
AgentRx: A Benchmark Study of LLM Agents for Multimodal Clinical Prediction Tasks
Single-agent LLM frameworks outperform naive multi-agent systems in multimodal clinical risk prediction tasks and are better calibrated.
-
Is a team only as strong as its weakest link? Quantifying the short-board effect with AI Agents
LLM multi-agent simulations reveal a cumulative product effect from multiple weak links on team performance and identify distinct capability regimes including a Sisyphus predicament.
-
TRUST: A Framework for Decentralized AI Service v.0.1
TRUST is a decentralized AI auditing framework that decomposes reasoning into HDAGs, maps agent interactions via the DAAN protocol to CIGs, and uses stake-weighted multi-tier consensus to achieve 72.4% accuracy while proving a Safety-Profitability Theorem that rewards honest auditors.
-
Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems
Sovereign Agentic Loops decouple LLM reasoning from execution by emitting validated intents through a control plane with obfuscation and evidence chains, blocking 93% of unsafe actions in a cloud prototype while adding 12.4 ms latency.
-
Mesh Memory Protocol: Semantic Infrastructure for Multi-Agent LLM Systems
MMP defines a seven-field CMB schema, role-based SVAF evaluation, content-hash lineage, and remix storage to enable traceable cross-session collaboration among autonomous LLM agents.
-
More Is Different: Toward a Theory of Emergence in AI-Native Software Ecosystems
AI-native software ecosystems exhibit emergent behaviors best explained by complex adaptive systems theory, requiring new ecosystem-level monitoring and seven testable propositions that may extend or replace Lehman's laws.
-
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Claude Code centers on a model-tool while-loop surrounded by permission systems, context compaction, extensibility hooks, subagent delegation, and session storage; the same design questions yield different answers in OpenClaw's gateway context.