# Resource Consumption Threats in Large Language Models

arXiv: https://arxiv.org/abs/2603.16068 · HTML: https://mlsanity.com/paper/2603.16068/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 73 of its 100 references that are in the map.
- First posted on arXiv 17 Mar 2026.

## Builds on (most cited first, 30 of 73)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Survey on Large Language Model based Autonomous Agents](https://mlsanity.com/paper/2308.11432/) (2023)
- [The Rise and Potential of Large Language Model Based Agents: A Survey](https://mlsanity.com/paper/2309.07864/) (2023)
- [Reasoning with Language Model is Planning with World Model](https://mlsanity.com/paper/2305.14992/) (2023)
- [Taming Throughput-Latency Tradeoff in LLM Inference with Sarathi-Serve](https://mlsanity.com/paper/2403.02310/) (2024)
- [Neural Text Generation with Unlikelihood Training](https://mlsanity.com/paper/1908.04319/) (2019)
- [LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression](https://mlsanity.com/paper/2310.06839/) (2023)
- [AutoAgents: A Framework for Automatic Agent Generation](https://mlsanity.com/paper/2309.17288/) (2023)
- [From Words to Watts: Benchmarking the Energy Costs of Large Language Model Inference](https://mlsanity.com/paper/2310.03003/) (2023)
- [CoT-Valve: Length-Compressible Chain-of-Thought Tuning](https://mlsanity.com/paper/2502.09601/) (2025)
- [SafeChain: Safety of Language Models with Long Chain-of-Thought Reasoning Capabilities](https://mlsanity.com/paper/2502.12025/) (2025)
- [Sponge Examples: Energy-Latency Attacks on Neural Networks](https://mlsanity.com/paper/2006.03463/) (2020)
- [Concise Thoughts: Impact of Output Length on LLM Reasoning and Cost](https://mlsanity.com/paper/2407.19825/) (2024)
- [A Review on Edge Large Language Models: Design, Execution, and Applications](https://mlsanity.com/paper/2410.11845/) (2024)
- [OverThink: Slowdown Attacks on Reasoning LLMs](https://mlsanity.com/paper/2502.02542/) (2025)
- [Learning to Break the Loop: Analyzing and Mitigating Repetitions for Neural Text Generation](https://mlsanity.com/paper/2206.02369/) (2022)
- [SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference](https://mlsanity.com/paper/2307.02628/) (2023)
- [A Theoretical Analysis of the Repetition Problem in Text Generation](https://mlsanity.com/paper/2012.14660/) (2020)
- [Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers](https://mlsanity.com/paper/2305.15805/) (2023)
- [Auto-Regressive Next-Token Predictors are Universal Learners](https://mlsanity.com/paper/2309.06979/) (2023)
- [Make Every Penny Count: Difficulty-Adaptive Self-Consistency for Cost-Efficient Reasoning](https://mlsanity.com/paper/2408.13457/) (2024)
- [A Panda? No, It's a Sloth: Slowdown Attacks on Adaptive Multi-Exit Neural Network Inference](https://mlsanity.com/paper/2010.02432/) (2020)
- [Energy Considerations of Large Language Model Inference and Efficiency Optimizations](https://mlsanity.com/paper/2504.17674/) (2025)
- [NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models](https://mlsanity.com/paper/2203.15859/) (2022)
- [Induction Heads as an Essential Mechanism for Pattern Matching in In-context Learning](https://mlsanity.com/paper/2407.07011/) (2024)
- [Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective](https://mlsanity.com/paper/2310.10226/) (2023)
- [Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settings](https://mlsanity.com/paper/2412.13879/) (2024)
- [From Self-Attention to Markov Models: Unveiling the Dynamics of Generative Transformers](https://mlsanity.com/paper/2402.13512/) (2024)
- [An Engorgio Prompt Makes Large Language Model Babble on](https://mlsanity.com/paper/2412.19394/) (2024)

## Built on by (most cited first, 2 of 2)

- [Uncovering Uncontrolled Repetition through Residual Stream Dynamics](https://mlsanity.com/paper/2609.38802/) (2026)
- [When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoning](https://mlsanity.com/paper/2609.38817/) (2026)

## Abstract (arXiv)

Given limited and costly computational infrastructure, resource efficiency is a key requirement for large language models (LLMs). Efficient LLMs increase service capacity for providers and reduce latency and API costs for users. Recent resource consumption threats induce excessive generation, degrading model efficiency and harming both service availability and economic sustainability. This survey presents a systematic review of threats to resource consumption in LLMs. We further establish a unified view of this emerging area by clarifying its scope and examining the problem along the full pipeline from threat induction to mechanism understanding and mitigation. Our goal is to clarify the problem landscape for this emerging area, thereby providing a clearer foundation for characterization and mitigation.