STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning

• URL: http://arxiv.org/abs/2506.18831v1
• Date: Mon, 23 Jun 2025 16:47:19 GMT
• Title: STU-PID: Steering Token Usage via PID Controller for Efficient Large Language Model Reasoning
• Authors: Aryasomayajula Ram Bharadwaj,
• Abstract summary: Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon.<n>We propose STUPID, a novel training-free method that employs a PID controller to dynamically activation modulate steering strength during inference.<n>Our approach combines a chunk-level classifier for detecting redundant reasoning patterns with a PID control mechanism that adaptively adjusts steering intensity based on the predicted redundancy probability.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large Language Models employing extended chain-of-thought (CoT) reasoning often suffer from the overthinking phenomenon, generating excessive and redundant reasoning steps that increase computational costs while potentially degrading performance. While recent work has explored static steering approaches to mitigate this issue, they lack the adaptability to dynamically adjust intervention strength based on real-time reasoning quality. We propose STUPID (Steering Token Usage via PID controller), a novel training-free method that employs a PID controller to dynamically modulate activation steering strength during inference. Our approach combines a chunk-level classifier for detecting redundant reasoning patterns with a PID control mechanism that adaptively adjusts steering intensity based on the predicted redundancy probability. Experimental evaluation on GSM8K demonstrates that STUPID achieves a 6% improvement in accuracy while reducing token usage by 32%, outperforming static steering baselines. Our method provides a principled framework for dynamic reasoning calibration that maintains reasoning quality while significantly improving computational efficiency.

Related papers

• LAPO: Internalizing Reasoning Efficiency via Length-Adaptive Policy Optimization [48.91511514636768]
  We present Length-Adaptive Policy Optimization (LAPO), a framework that transforms reasoning length control from an external constraint into an intrinsic model capability.<n>LAPO enables models to internalize an understanding of appropriate reasoning depth through a two-stage reinforcement learning process.<n> Experiments on mathematical reasoning benchmarks demonstrate that LAPO reduces token usage by up to 40.9% while improving accuracy by 2.3%.
  arXiv  Detail & Related papers  (2025-07-21T16:14:41Z)
• KV Cache Steering for Inducing Reasoning in Small Language Models [44.97633860257524]
  We propose cache steering, a lightweight method for implicit steering of language models.<n>We apply cache steering to induce chain-of-thought reasoning in small language models.
  arXiv  Detail & Related papers  (2025-07-11T17:59:36Z)
• KAT-V1: Kwai-AutoThink Technical Report [50.84483585850113]
  We present Kwaipilot-AutoThink (KAT), an open-source 40B large language model developed to address the overthinking problem in reasoning-intensive tasks.<n>KAT dynamically switches between reasoning and non-reasoning modes based on task complexity.<n>We also propose Step-SRPO, a reinforcement learning algorithm that incorporates intermediate supervision into the GRPO framework.
  arXiv  Detail & Related papers  (2025-07-11T04:07:10Z)
• ConciseHint: Boosting Efficient Reasoning via Continuous Concise Hints during Generation [53.149817480019834]
  Recent advancements in large reasoning models (LRMs) have achieved notable performance enhancements on complex reasoning tasks by scaling up the generation length by Chain-of-Thought (CoT)<n>We propose a framework dubbed ConciseHint, which continuously encourages the reasoning model to speak concisely by injecting the textual hint during the token generation of the reasoning process.<n>Experiments on the state-of-the-art LRMs, including DeepSeek-R1 and Qwen-3 series, demonstrate that our method can effectively produce concise reasoning processes while maintaining performance well.
  arXiv  Detail & Related papers  (2025-06-23T16:20:44Z)
• Exploring and Exploiting the Inherent Efficiency within Large Reasoning Models for Self-Guided Efficiency Enhancement [101.77467538102924]
  Large reasoning models (LRMs) exhibit overthinking, which hinders efficiency and inflates inference cost.<n>We propose two lightweight methods to enhance LRM efficiency.<n>First, we introduce Efficiency Steering, a training-free activation steering technique that modulates reasoning behavior via a single direction.<n>Second, we develop Self-Rewarded Efficiency RL, a reinforcement learning framework that dynamically balances task accuracy and brevity.
  arXiv  Detail & Related papers  (2025-06-18T17:18:12Z)
• Accelerated Test-Time Scaling with Model-Free Speculative Sampling [58.69141724095398]
  We introduce STAND (STochastic Adaptive N-gram Drafting), a novel model-free speculative decoding approach.<n>We show that STAND reduces inference latency by 60-65% compared to standard autoregressive decoding.<n>As a model-free approach, STAND can be applied to any existing language model without additional training.
  arXiv  Detail & Related papers  (2025-06-05T07:31:18Z)
• Self-Route: Automatic Mode Switching via Capability Estimation for Efficient Reasoning [36.470695895695044]
  Self-Route is a dynamic reasoning framework that automatically selects between general and reasoning modes.<n>We show that Self-Route achieves comparable accuracy to reasoning models while reducing token consumption by 30-55%.
  arXiv  Detail & Related papers  (2025-05-27T03:18:31Z)
• Let LLMs Break Free from Overthinking via Self-Braking Tuning [60.08396797526657]
  Large reasoning models (LRMs) have significantly enhanced their reasoning capabilities by generating longer chains of thought.<n>This performance gain comes at the cost of a substantial increase in redundant reasoning during the generation process.<n>We propose a novel framework, Self-Braking Tuning (SBT), which tackles overthinking from the perspective of allowing the model to regulate its own reasoning process.
  arXiv  Detail & Related papers  (2025-05-20T16:53:40Z)
• Bisimulation metric for Model Predictive Control [44.301098448479195]
  Bisimulation Metric for Model Predictive Control (BS-MPC) is a novel approach that incorporates bisimulation metric loss in its objective function to directly optimize the encoder. BS-MPC improves training stability, robustness against input noise, and computational efficiency by reducing training time. We evaluate BS-MPC on both continuous control and image-based tasks from the DeepMind Control Suite.
  arXiv  Detail & Related papers  (2024-10-06T17:12:10Z)
• PID Control-Based Self-Healing to Improve the Robustness of Large Language Models [23.418411870842178]
  Minor perturbations can significantly reduce the performance of well-trained language models. We construct a computationally efficient self-healing process to correct undesired model behavior. The proposed PID control-based self-healing is a low cost framework that improves the robustness of pre-trained large language models.
  arXiv  Detail & Related papers  (2024-03-31T23:46:51Z)
• Self-Tuning PID Control via a Hybrid Actor-Critic-Based Neural Structure for Quadcopter Control [0.0]
  Proportional-Integrator-Derivative (PID) controller is used in a wide range of industrial and experimental processes. Due to the uncertainty of model parameters and external disturbances, real systems such as Quadrotors need more robust and reliable PID controllers. In this research, a self-tuning PID controller using a Reinforcement-Learning-based Neural Network has been investigated.
  arXiv  Detail & Related papers  (2023-07-03T19:35:52Z)
• Performance-Driven Controller Tuning via Derivative-Free Reinforcement Learning [6.5158195776494]
  We tackle the controller tuning problem using a novel derivative-free reinforcement learning framework. We conduct numerical experiments on two concrete examples from autonomous driving, namely, adaptive cruise control with PID controller and trajectory tracking with MPC controller. Experimental results show that the proposed method outperforms popular baselines and highlight its strong potential for controller tuning.
  arXiv  Detail & Related papers  (2022-09-11T13:01:14Z)
• Online Reinforcement Learning Control by Direct Heuristic Dynamic Programming: from Time-Driven to Event-Driven [80.94390916562179]
  Time-driven learning refers to the machine learning method that updates parameters in a prediction model continuously as new data arrives. It is desirable to prevent the time-driven dHDP from updating due to insignificant system event such as noise. We show how the event-driven dHDP algorithm works in comparison to the original time-driven dHDP.
  arXiv  Detail & Related papers  (2020-06-16T05:51:25Z)

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.