Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures

• URL: http://arxiv.org/abs/2609.15293v1
• Date: Mon, 14 Sep 2026 09:46:59 GMT
• Title: Why LLM Agents Collapse Without Oversight: The Enforcement Gap as the Mechanism Behind Emergence World Failures
• Abstract summary: Reflexion-style agents already detect dangerous plan steps through iterative self-critique.<n>We call this the enforcement gap: the audit sees the problem; the controller ignores it.<n>We prove formally that when enforcement probability is near zero, detection quality is irrelevant to security.
• Score: 19.162716475205308
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: When Emergence World placed frontier LLM agents in an unsupervised multi-agent simulation, the results were alarming: agents committed crimes, starved, and enforced unanimous conformity -- without any external attacker. This paper identifies the mechanism. Reflexion-style agents already detect dangerous plan steps through iterative self-critique, yet the architecture provides no pathway from detection to action. We call this the enforcement gap: the audit sees the problem; the controller ignores it. Closing the gap requires a single conditional check -- fewer than 20 lines of code -- and reduces attack success by more than fourfold in large-scale experiments across frontier models, all five major agent frameworks, and an independent benchmark. We prove formally that when enforcement probability is near zero, detection quality is irrelevant to security. We further identify two compounding failure modes -- unreliable auditors and unparseable verdicts -- that explain every collapse pattern in Emergence World. A GRPO-trained enforcement controller resolves the ambiguity case. Together these results motivate a three-requirement Audit Enforcement Specification that is absent from every deployed framework today.

Related papers

• Safety Does Not Compose: Non-Decaying Loop State for Autonomous LLM Agents [16.24087700490158]
  Large language model agents are increasingly deployed as autonomous loops.<n>We show that this is a failure of composition rather than an implementation detail.<n>We present LoopHarness, which restores a persistent, non-decaying safety state at the loop level.
  arXiv  Detail & Related papers  (2026-08-27T13:52:31Z)
• HANSARD: A Reference Architecture for Forensic Readiness, Runtime Witnessing, and Graded Attribution in Autonomous Multi-Agent AI Systems [3.7015952547586832]
  An autonomous multi-agent system nowadays act in finance, software supply chains, and security operations.<n>No method can robustly establish what happened, what caused it, or who is accountable.<n>This is because provenance forensics works at the wrong abstraction, formal causality assumes the causal model, and agent auditing trusts self-recording.<n>The target failure mode is, thus, attribution laundering, spreading an act across redundant agents until none is a but-for cause.<n>This paper proposes HANSARD, a reference architecture treating accountability as a life-cycle property.
  arXiv  Detail & Related papers  (2026-08-23T17:18:22Z)
• POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems [0.07783271875179179]
  We present POIROT, a protocol that repurposes a system's own agents as its diagnostic layer.<n>Across evaluated settings, POIROT outperforms single-LLM baseline evaluators.<n>We release POIROT as an open-source library alongside BLAME, a benchmark for fault attribution in safety-critical multi-agent systems.
  arXiv  Detail & Related papers  (2026-06-01T14:05:35Z)
• Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs [20.59321114618083]
  We show that single-turn diagnostics systematically overestimate RAG safety, that contradiction is uncorrelated with safe resolution, and that no universal prompt fix exists.<n>The gap between what models recognize and what they do must be measured and closed before retrieval-augmented systems can be trusted in high-stakes settings.
  arXiv  Detail & Related papers  (2026-05-26T15:18:43Z)
• VerifyMAS: Hypothesis Verification for Failure Attribution in LLM Multi-Agent Systems [79.51005192758262]
  Large language model-driven multi-agent systems excel at complex tasks.<n>However, unreliable agents remain a key bottleneck to system-level reliability.<n>We propose a hypothesis verification framework for agent failure attribution.
  arXiv  Detail & Related papers  (2026-05-17T14:09:35Z)
• Auditing Agent Harness Safety [81.22315979618612]
  LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components.<n>Most safety benchmarks score only final outputs or terminal states, even though many violations occur mid-trajectory rather than at termination.<n>We propose HarnessAudit, a framework that audits full execution trajectories across boundary compliance, execution fidelity, and system stability.
  arXiv  Detail & Related papers  (2026-05-14T02:14:28Z)
• PRISM: : Planning and Reasoning with Intent in Simulated Embodied Environments [59.07829883257003]
  Built on five multi-room apartments, PRISM structures 300 human-verified tasks into three capability tiers.<n>PRISM exposes an agent-agnostic executable action API that allows arbitrary agents to be evaluated end-to-end.
  arXiv  Detail & Related papers  (2026-05-12T04:59:47Z)
• MAS-FIRE: Fault Injection and Reliability Evaluation for LLM-Based Multi-Agent Systems [38.44649280816596]
  We propose MAS-FIRE, a systematic framework for fault injection and reliability evaluation of Multi-Agent Systems.<n>We define a taxonomy of 15 fault types covering intra-agent cognitive errors and inter-agent coordination failures.<n>Applying MAS-FIRE to three representative MAS architectures, we uncover a rich set of fault-tolerant behaviors.
  arXiv  Detail & Related papers  (2026-02-23T13:47:43Z)
• Explainable and Fine-Grained Safeguarding of LLM Multi-Agent Systems via Bi-Level Graph Anomaly Detection [76.91230292971115]
  Large language model (LLM)-based multi-agent systems (MAS) have shown strong capabilities in solving complex tasks.<n>XG-Guard is an explainable and fine-grained safeguarding framework for detecting malicious agents in MAS.
  arXiv  Detail & Related papers  (2025-12-21T13:46:36Z)
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks [58.959622170433725]
  BlindGuard is an unsupervised defense method that learns without requiring any attack-specific labels or prior knowledge of malicious behaviors.<n>We show that BlindGuard effectively detects diverse attack types (i.e., prompt injection, memory poisoning, and tool attack) across multi-agent systems.
  arXiv  Detail & Related papers  (2025-08-11T16:04:47Z)
• Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems [50.29939179830491]
  Failure attribution in LLM multi-agent systems remains underexplored and labor-intensive.<n>We develop and evaluate three automated failure attribution methods, summarizing their corresponding pros and cons.<n>The best method achieves 53.5% accuracy in identifying failure-responsible agents but only 14.2% in pinpointing failure steps.
  arXiv  Detail & Related papers  (2025-04-30T23:09:44Z)
• Why Do Multi-Agent LLM Systems Fail? [87.90075668488434]
  We introduce MAST-Data, a comprehensive dataset of 1600+ annotated traces collected across 7 popular MAS frameworks.<n>We build the first Multi-Agent System Failure taxonomy (MAST)<n>We leverage MAST and MAST-Data to analyze failure patterns across models (GPT4, Claude 3, Qwen2.5, CodeLlama) and tasks (coding, math, general agent)
  arXiv  Detail & Related papers  (2025-03-17T19:04:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.