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

[2506.18831] Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2506.18831 (cs) [Submitted on 23 Jun 2025 ( v1 ), last revised 15 Jun 2026 (this version, v3)] Title: Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control Authors: Aryasomayajula Ram Bharadwaj View a PDF of the paper titled Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control, by Aryasomayajula Ram Bharadwaj View PDF HTML (experimental) Abstract: Reasoning LLMs trained with long chain-of-thought often overthink: they spend tokens on redundant reflection and transitions that inflate cost without improving accuracy. Static activation steering (e.g.\ SEAL) suppresses such content with a fixed vector, but applies the same strength regardless of how redundant the current chunk actually is. We describe PID-steering, a training-free, decoding-time method that modulates the steering strength with a PID controller driven by a lightweight chunk-level redundancy classifier. On a subset of GSM8K with DeepSeek-R1-Distill-Qwen-1.5B, the method improves accuracy from 85.7\% to 89.6\% (+3.9 pp) while cutting average output length from 1026 to 790 tokens ($-$23\%). We report it as a small-scale proof of concept rather than a benchmark result. Subjects: Computation and Language (cs.CL) Cite as: arXiv:2506.18831 [cs.CL] (or arXiv:2506.18831v3 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2506.18831 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Ram Bharadwaj Aryasomayajula Mr [ view email ] [v1] Mon, 23 Jun 2025 16:47:19 UTC (73 KB) [v2] Sat, 11 Apr 2026 12:29:43 UTC (69 KB) [v3] Mon, 15 Jun 2026 20:03:11 UTC (173 KB) Full-text links: Access Paper: View a PDF of the paper titled Adaptive Activation Steering for Efficient LLM Reasoning via Closed-Loop PID Control, by Aryasomayajula Ram Bharadwaj View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2025-06 Change to browse by: cs References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• One Token Is Enough: Fingerprinting and Verifying Large Language Models from Single-Token Output Distributions#363194
• Parameterized model checking of token-passing systems#644418
• Long-Context Demonstration Selection Using State Space Models#1011603
• Towards Reasoning in Large Language Models: A Survey#16662
• DODR: Deterministic Operator-Driven Reasoning in Latent Space#971450