Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning

• URL: http://arxiv.org/abs/2607.29211v1
• Date: Fri, 31 Jul 2026 09:30:33 GMT
• Title: Knowing When to Quit: Diagnosing and Training LLMs to Abort Futile Reasoning
• Abstract summary: Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks.<n>We introduce textbfCaRL (textbfCapability-textbfaligned textbfReinforcement textbfL) to align behavior with capability boundaries.<n>Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties.
• Score: 109.33717747526583
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Large language models generate computationally expensive yet semantically void reasoning on beyond-capability tasks, creating risks where plausible-sounding but incorrect derivations mislead users. We characterize this \textit{futile reasoning} phenomenon through systematic analysis, revealing universal capability overreach and systematic miscalibration between capability and behavior. The dominant failure mode is specious reasoning, which outputs look superficially valid but contain subtle errors, escalating with task difficulty. To address this, we introduce \textbf{CaRL} (\textbf{Ca}pability-\textbf{a}ligned \textbf{R}einforcement \textbf{L}earning), which aligns model behavior with capability boundaries through reward shaping that incentivizes refusal over futile reasoning and hindsight refusal augmentation that converts failures into refusal supervision. Experiments demonstrate a substantial reduction in futile reasoning while preserving performance across task difficulties, effectively achieving capability-aligned behavior without sacrificing utility. \footnote{https://github.com/icip-cas/Knowing-When-to-Quit}

Related papers

• On the Limits of Prompt-Conditioned Language Models as General-Purpose Learners [4.675635684281315]
  Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks.<n>We argue that this view overlooks a fundamental constraint: language is a compressed and capacity-limited interface for conveying task information.<n>We analyse how latent tasks are encoded into prompts and reinterpreted under alignment and safety constraints.
  arXiv  Detail & Related papers  (2026-06-22T17:52:59Z)
• CoFEE: Reasoning Control for LLM-Based Feature Discovery [0.0]
  We study reasoning control in Large Language Models (LLMs) by inducing cognitive behaviors for improving feature discovery.<n>We introduce CoFEE, a reasoning framework that enforces cognitive behaviors in how the LLM reasons during feature discovery.<n>CoFEE achieves an average Success Rate Score that is 15.2% higher than the vanilla approach, while generating 29% fewer features and reducing costs by 53.3%.
  arXiv  Detail & Related papers  (2026-04-23T12:05:38Z)
• Pause or Fabricate? Training Language Models for Grounded Reasoning [50.104657152302956]
  We propose Grounded Reasoning via Interactive Reinforcement Learning (GRIL) for grounded reasoning under incomplete information.<n>GRIL decomposes the reasoning process into two stages: clarify and pause, which identifies whether the available information is sufficient, and grounded reasoning, which performs task solving once the necessary premises are established.<n>Experiments on GSM8K-Insufficient and MetaMATH-Insufficient show that GRIL significantly improves premise detection (up to 45%), leading to a 30% increase in task success while reducing average response length by over 20%.
  arXiv  Detail & Related papers  (2026-04-21T16:45:29Z)
• Bridging the Know-Act Gap via Task-Level Autoregressive Reasoning [22.264933226031435]
  We present a comprehensive analysis using FaultyScience, a newly constructed large-scale, cross-disciplinary benchmark of faulty questions.<n>We show that the gap is pervasive and stems from token-level autoregression, which entangles task selection with content generation.<n>We propose DeIllusionLLM, a task-level autoregressive framework that explicitly models this decision.
  arXiv  Detail & Related papers  (2026-03-23T22:43:34Z)
• When and Why Does Unsupervised RL Succeed in Mathematical Reasoning? A Manifold Envelopment Perspective [23.239530219575936]
  Outcome-based reinforcement learning (RL) significantly advances the mathematical reasoning capabilities of Large Language Models (LLMs)<n>Its reliance on computationally expensive ground-truth annotations imposes a severe scalability bottleneck.<n>Unsupervised RL guided by intrinsic rewards offers a scalable alternative.
  arXiv  Detail & Related papers  (2026-03-17T14:29:38Z)
• Imagination Helps Visual Reasoning, But Not Yet in Latent Space [65.80396132375571]
  We investigate the validity of latent reasoning using Causal Mediation Analysis.<n>We show that latent tokens encode limited visual information and exhibit high similarity.<n>We propose a straightforward alternative named CapImagine, which teaches the model to explicitly imagine using text.
  arXiv  Detail & Related papers  (2026-02-26T08:56:23Z)
• ALIVE: Awakening LLM Reasoning via Adversarial Learning and Instructive Verbal Evaluation [4.265094703231012]
  We introduce textbfALIVE (emphAdrial Learning with Instructive Verbal Evaluation), a hands-free alignment framework.<n>By coupling adversarial learning with instructive verbal feedback, ALIVE enables models to internalize evaluative criteria directly from raw corpora.<n>With identical data and compute, ALIVE achieves markedly improved cross-domain generalization, and higher self-correction rates.
  arXiv  Detail & Related papers  (2026-02-05T09:20:23Z)
• On the Paradoxical Interference between Instruction-Following and Task Solving [50.75960598434753]
  Instruction following aims to align Large Language Models (LLMs) with human intent by specifying explicit constraints on how tasks should be performed.<n>We reveal a counterintuitive phenomenon: instruction following can paradoxically interfere with LLMs' task-solving capability.<n>We propose a metric, SUSTAINSCORE, to quantify the interference of instruction following with task solving.
  arXiv  Detail & Related papers  (2026-01-29T17:48:56Z)
• Beware of Reasoning Overconfidence: Pitfalls in the Reasoning Process for Multi-solution Tasks [54.31998314008198]
  Large Language Models (LLMs) excel in reasoning tasks requiring a single correct answer, but they perform poorly in multi-solution tasks.<n>We attribute this limitation to textbfreasoning overconfidence: a tendency to express undue certainty in an incomplete solution set.<n>We propose the textbfcognitive-rigidity hypothesis, which posits that overconfidence arises when the reasoning process prematurely converges on a narrow set of thought paths.
  arXiv  Detail & Related papers  (2025-12-01T14:35:06Z)
• Sycophancy Mitigation Through Reinforcement Learning with Uncertainty-Aware Adaptive Reasoning Trajectories [58.988535279557546]
  We introduce textbf sycophancy Mitigation through Adaptive Reasoning Trajectories.<n>We show that SMART significantly reduces sycophantic behavior while preserving strong performance on out-of-distribution inputs.
  arXiv  Detail & Related papers  (2025-09-20T17:09:14Z)
• Causality-aligned Prompt Learning via Diffusion-based Counterfactual Generation [45.395353088233556]
  We introduce a theoretically grounded $textbfDi$ffusion-based $textbfC$ounterf$textbfa$ctual $textbfp$rompt learning framework.<n>Our method performs excellently across tasks such as image classification, image-text retrieval, and visual question answering, with particularly strong advantages in unseen categories.
  arXiv  Detail & Related papers  (2025-07-26T09:27:52Z)
• Interpreting the Repeated Token Phenomenon in Large Language Models [31.1226642501095]
  Large Language Models (LLMs) often fail to accurately repeat a single word when prompted to, and instead output unrelated text.<n>We aim to explain the causes for this phenomenon and link it to the concept of attention sinks''<n>Our investigation identifies the neural circuit responsible for attention sinks and shows how long repetitions disrupt this circuit.
  arXiv  Detail & Related papers  (2025-03-11T21:40:58Z)
• Tuning-Free Accountable Intervention for LLM Deployment -- A Metacognitive Approach [55.613461060997004]
  Large Language Models (LLMs) have catalyzed transformative advances across a spectrum of natural language processing tasks. We propose an innovative textitmetacognitive approach, dubbed textbfCLEAR, to equip LLMs with capabilities for self-aware error identification and correction.
  arXiv  Detail & Related papers  (2024-03-08T19:18:53Z)
• 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.