Tag
This paper proposes Interaction-Effect Propagation (IE-Prop), a model that estimates and propagates error risk in LLM-based multi-agent systems by learning separate effects for correct and incorrect upstream agents, showing consistent AUROC gains over baselines across three architectures and benchmarks.
该论文提出"错误复现"（error reproduction）机制，指出在LLM智能体外部记忆中持久化抽象规则会循环放大错误，并提出Anti-Persistence记忆设计：仅累积轨迹与结果、按需临时合成指导，从而在多个基准上取得更高成功率与更低LLM调用成本。
An opinion piece arguing that AI agent evaluations should measure not just accuracy and speed, but how far a consequential error can propagate across connected systems before detection and containment, and proposing safeguards like staged execution and transaction caps for high-impact actions.
This paper measures how AI agents contaminate stores they write to, identifying a threshold for error propagation and validating findings with synthetic and real-world Wikidata data.
This paper measures the reliability of tool-using agents at the invocation level, revealing that under exact-match scoring, error propagation parameters are fixed by the scoring rule and proposes a conditional-on-state scoring method to address this.
The paper introduces AgenticRAG-FP, an interventional benchmark for causal failure attribution in agentic RAG systems, analyzing how failures propagate across retrieval hops and evaluating diagnosis performance.
This paper models hallucination propagation in multi-agent LLM pipelines as a Markov process, showing that errors become less detectable across stages and proposing early verification to reduce survival rates.
Explores how multi-layered AI agent delegation affects reliability, arguing that the downstream influence of errors matters more than the number of layers.
This paper formalizes the 'Granularity Paradox' in time-series forecasting, showing that finer temporal disaggregation improves in-sample fit but degrades out-of-sample accuracy due to recursive error propagation, and benchmarks multiple models across granularities.
This paper studies how reasoning exchange among multiple AI agents can improve accuracy but also risk error propagation, proposing a runtime monitoring framework to prevent such propagation.
Introduces energy conservation as a hard physical constraint on inter-module information flow in modular neural networks, enforcing exact preservation of activation energy at module boundaries to attenuate error propagation. Experiments on CIFAR-10 and a robotic pipeline show significant improvements in noise robustness.
This paper introduces CHARM, a framework for detecting and mitigating cascading hallucinations in multi-step agentic RAG pipelines, where early-stage errors propagate and amplify across reasoning steps. CHARM achieves an 89.4% cascade detection rate and 82.1% error propagation reduction across multiple benchmarks with low latency overhead.
A developer discusses cascading failures in a 3-agent SDR system, where hallucinations propagate through agents, and seeks advice on improving reliability with human-in-loop or framework switching.