How Do Hardware Faults Manifest Differently in LLM Agents?
We present the first systematic study of the resilience of large language model (LLM) agents to random hardware-induced faults.
ProofPaper ↗
Key points
- Prior work on hardware fault resilience in LLMs focuses on model-level outcomes, such as incorrect outputs or generation failures.
- Yet LLM agents repeatedly interact with tools and environments, creating loops that can change how hardware faults manifest.
- We conduct an extensive evaluation across three agent benchmarks, comprising 6,814 agent executions: 2,400+ clean runs and 4,300+ fault-injected runs with independently sampled random two-bit weight faults.
- We trace how these faults propagate through agent execution.
Sources (1)
- [1]How Do Hardware Faults Manifest Differently in LLM Agents?arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 10:08 PM
We present the first systematic study of the resilience of large language model (LLM) agents to random hardware-induced faults.
Prior work on hardware fault resilience in LLMs focuses on model-level outcomes, such as incorrect outputs or generation failures.
Extractive summary: sentences quoted from the sources.
Before this
- Oct 8, 2026GeoFitBench-LLM: A Benchmark for Assessing Large Language Models' Capabilities in Geospatial Data Requirements Elicitation for Geo-Analytic Tasks
- Oct 8, 2026GeopoliticalQA: Benchmarking Retrieval and Generation over Intelligence Reports
- Oct 8, 2026Knowing Is Not Telling: Identity Ossification in LLM Representations of Trans-border Communities
- Oct 8, 2026Understanding Jev, the new model everyone is talking about
- Oct 8, 2026Launching an opt-in vulnerability-finding service for open-source software
- Oct 7, 2026browser-use/browser-use 0.13.11