mlsanityData to 7 Oct 2026

RECUR: Resource Exhaustion Attack via Recursive-Entropy Guided Counterfactual Utilization and Reflection

arXiv 2602.08214 ↗First posted 9 Feb 2026cs.AI cs.CRcited by 4

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Large Reasoning Models (LRMs) employ reasoning to address complex tasks. Such explicit reasoning requires extended context lengths, resulting in substantially higher resource consumption. Prior work has shown that adversarially crafted inputs can trigger redundant reasoning processes, exposing LRMs to resource-exhaustion vulnerabilities. However, the reasoning process itself, especially its reflective component, has received limited attention, even though it can lead to over-reflection and consume excessive computing power. In this paper, we introduce Recursive Entropy to quantify the risk of resource consumption in reflection, thereby revealing the safety issues inherent in inference itself. Based on Recursive Entropy, we introduce RECUR, a resource exhaustion attack via Recursive Entropy guided Counterfactual Utilization and Reflection. It constructs counterfactual questions to verify the inherent flaws and risks of LRMs. Extensive experiments demonstrate that, under benign inference, recursive entropy exhibits a pronounced decreasing trend. RECUR disrupts this trend, increasing the output length by up to 11x and decreasing throughput by 90%. Our work provides a new perspective on robust reasoning.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 27 of its 33 references that are in the map. First posted on arXiv 9 Feb 2026.

Builds on

27 of 33 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025ThinkTrap: Denial-of-Service Attacks against Black-box LLM Services via Infinite Thinking8 Dec
  2. 2025POT: Inducing Overthinking in LLMs via Black-Box Iterative Optimization23 Aug
  3. 2025Excessive Reasoning Attack on Reasoning LLMs17 Jun
  4. 2025OverThink: Slowdown Attacks on Reasoning LLMs4 Feb

Other references · 23

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  2. 2021Training Verifiers to Solve Math Word Problemscited by 9,743
  3. 2021Evaluating Large Language Models Trained on Codecited by 8,053
  4. 2020Measuring Massive Multitask Language Understandingcited by 7,768
  5. 2025Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilitiescited by 3,655
  6. 2023Let's Verify Step by Stepcited by 3,598
  7. 2025s1: Simple test-time scalingcited by 1,311
  8. 2025Kimi k1.5: Scaling Reinforcement Learning with LLMscited by 1,193
  9. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 755
  10. 2024Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMscited by 564
  11. 2025Stop Overthinking: A Survey on Efficient Reasoning for Large Language Modelscited by 456
  12. 2025Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Modelscited by 381
11 more
  1. 2024Chain-of-Thought Reasoning Without Promptingcited by 208
  2. 2024A Careful Examination of Large Language Model Performance on Grade School Arithmeticcited by 188
  3. 2025A Survey of Reinforcement Learning for Large Reasoning Modelscited by 175
  4. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  5. 2024Coercing LLMs to do and reveal (almost) anythingcited by 88
  6. 2025On Entropy Control in LLM-RL Algorithmscited by 39
  7. 2024Crabs: Consuming Resource via Auto-generation for LLM-DoS Attack under Black-box Settingscited by 33
  8. 2024An Engorgio Prompt Makes Large Language Model Babble oncited by 30
  9. 2025ExtendAttack: Attacking Servers of LRMs via Extending Reasoningcited by 10
  10. 2025LoopLLM: Transferable Energy-Latency Attacks in LLMs via Repetitive Generationcited by 7
  11. 2025Breaking the Loop: Detecting and Mitigating Denial-of-Service Vulnerabilities in Large Language Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026Resource Consumption Threats in Large Language Modelscited by 2
  2. 2026From Shield to Target: Denial-of-Service Attacks on LLM-Based Agent Guardrailscited by 1
  3. 2026RecurGuard: Runtime Monitoring for Reasoning-Token Consumption Attackscited by 0
  4. 2026When Reasoning Goes Astray: Attention Dynamics of Uncontrolled Reasoningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026On the Efficiency-Safety Dilemma in Large Reasoning Models
  2. 2025BadReasoner: Planting Tunable Overthinking Backdoors into Large Reasoning Models for Fun or Profit
  3. 2025ReasoningGuard: Safeguarding Large Reasoning Models with Inference-time Safety Aha Moments
  4. 2026ENTRA: Entropy-Based Redundancy Avoidance in Large Language Model Reasoning
  5. 2025Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
  6. 2025HauntAttack: When Attack Follows Reasoning as a Shadow
  7. 2026Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty
  8. 2025Reuse, Don't Recompute: Efficient Large Reasoning Model Inference via Memory Orchestration