Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering

• URL: http://arxiv.org/abs/2607.18100v1
• Date: Mon, 20 Jul 2026 16:01:57 GMT
• Title: Can We Break LLMs Out of Self-Loops? Fine-Grained Reasoning Control with Activation Steering
• Abstract summary: We analyze and discover latent transition dynamics in the reasoning traces from Large Language Models.<n>We show that failure trajectories get stuck in self-loops, exhausting the token budget without progress toward the final answer.<n>We propose SOPHIA: Steering Of reasoning Processes via Hidden-state Intervention and Activations.
• Score: 44.273459587532535
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Extended reasoning has become standard for frontier Large Language Models (LLMs), yet the trajectories these models produce remain largely uncontrollable. Existing methods for shaping how a model reasons are prompt based approaches and operate at the input level, offering no fine-grained control over the reasoning process itself. Related work analyzes and discovers latent transition dynamics in the reasoning traces from Large Language Models. Building on this, we statistically characterize these states, and show that failure trajectories get stuck in self-loops, exhausting the token budget without progress toward the final answer. To intervene on these failures, We propose SOPHIA: Steering Of reasoning Processes via Hidden-state Intervention and Activations. We treat each reasoning trace as a sequence of latent states rather than an unstructured texts, and investigate whether inference time interventions can provide fine-grained control over the self-looping reasoning process. We classify every prefix to a latent state, record step level transitions, and use them to construct a bank of steering vectors indexed by state pairs. At inference time, a controller infers the current state and, given a target state, retrieves the corresponding vector and can also detect self-loops online from the transition structure to prevent the model from sinking into a reasoning black hole. Through extensive experiments, our method reliably intervenes on self-loop failures, with steering vectors that generalize to different state pairs. End task accuracy and token efficiency indicate that fine-grained controllability results in better reasoning quality.

Related papers

• Learning to Refine Hidden States for Reliable LLM Reasoning [0.21485350418225244]
  Large language models show strong reasoning ability, but their internal reasoning process can remain unstable in complex multi-step settings.<n>We propose ReLAR, a reinforcement-guided latent refinement framework that iteratively updates hidden representations before decoding.
  arXiv  Detail & Related papers  (2026-06-16T05:03:27Z)
• Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning [27.851326399978394]
  Large language models improve final-answer accuracy through extended chain-of-thought reasoning.<n>Existing efficient reasoning methods control thinking length by shortening, early-stopping, or compressing traces.<n>We propose Agentic Chain-of-Thought Steering (ACTS), which formulates reasoning steering as a Markov decision process.
  arXiv  Detail & Related papers  (2026-06-02T17:51:30Z)
• Why We Need World Models for AGI: Where LLMs Fail and How World Models May Outperform [1.6746114653388389]
  Large language models achieve strong performance in language generation and knowledge-intensive tasks.<n>We argue that these limitations may arise from an objective-level mismatch between sequence prediction and reasoning over latent environment dynamics.<n>We introduce Latent Dynamics Inference (LDI), a conceptual perspective that interprets language and multimodal observations as partial evidence of underlying transition dynamics.
  arXiv  Detail & Related papers  (2026-05-13T12:55:34Z)
• Rethinking State Tracking in Recurrent Models Through Error Control Dynamics [26.942965240880515]
  We show that affine recurrent networks cannot correct errors along state-separating subspaces once they preserve state representations.<n>We prove that robust state tracking is determined not only by an architecture's theoretical expressivity but crucially by its error control.
  arXiv  Detail & Related papers  (2026-05-08T13:59:15Z)
• Structured Reasoning for Large Language Models [59.215789462977206]
  We propose Structured Reasoning (SCR), a framework that decouples reasoning trajectories into explicit, evaluable, and trainable components.<n>SCR substantially improves reasoning efficiency and self-verification.<n>Compared with existing reasoning paradigms, it reduces output token length by up to 50%.
  arXiv  Detail & Related papers  (2026-01-12T04:04:01Z)
• From "Aha Moments" to Controllable Thinking: Toward Meta-Cognitive Reasoning in Large Reasoning Models via Decoupled Reasoning and Control [11.321315058502215]
  Large Reasoning Models (LRMs) have demonstrated a latent capacity for complex reasoning by spontaneously exhibiting cognitive behaviors such as step-by-step reasoning, reflection, and backtracking, commonly referred to as "Aha Moments"<n>However, such emergent behaviors remain unregulated and uncontrolled, often resulting in overthinking, where the model continues generating redundant reasoning content even after reaching reliable conclusions.<n>Current models are unable to monitor and adaptively manage their reasoning process to determine when to continue, backtrack, or terminate.<n>We propose the Meta-cognitive Reasoning Framework (MERA), which explicitly decouples the thinking process into distinct
  arXiv  Detail & Related papers  (2025-08-06T13:59:17Z)
• KV Cache Steering for Controlling Frozen LLMs [80.50365534625438]
  cache steering is 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)
• Fractional Reasoning via Latent Steering Vectors Improves Inference Time Compute [60.151643048803145]
  We propose Fractional Reasoning, a framework that enables continuous control over reasoning intensity at inference time.<n>Our method operates by extracting the latent steering vector associated with deeper reasoning and reapplying it with a tunable scaling factor.<n> Experiments on GSM8K, MATH500, and GPQA demonstrate that Fractional Reasoning consistently improves performance across diverse reasoning tasks and models.
  arXiv  Detail & Related papers  (2025-06-18T21:15:59Z)
• SEAL: Steerable Reasoning Calibration of Large Language Models for Free [58.931194824519935]
  Large Language Models (LLMs) have demonstrated compelling capabilities for complex reasoning tasks via the extended chain-of-thought (CoT) reasoning mechanism.<n>Recent studies reveal substantial redundancy in the CoT reasoning traces, which negatively impacts model performance.<n>We introduce SEAL, a training-free approach that seamlessly calibrates the CoT process, improving accuracy while demonstrating significant efficiency gains.
  arXiv  Detail & Related papers  (2025-04-07T02:42:07Z)
• A Closer Look at the Self-Verification Abilities of Large Language Models in Logical Reasoning [73.77088902676306]
  We take a closer look at the self-verification abilities of large language models (LLMs) in the context of logical reasoning. Our main findings suggest that existing LLMs could struggle to identify fallacious reasoning steps accurately and may fall short of guaranteeing the validity of self-verification methods.
  arXiv  Detail & Related papers  (2023-11-14T07:13:10Z)

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.