Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning

• URL: http://arxiv.org/abs/2602.08520v3
• Date: Thu, 12 Feb 2026 05:32:26 GMT
• Title: Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning
• Abstract summary: Reinforcement Inference uses the model's own uncertainty to selectively invoke a second, more deliberate reasoning attempt.<n>On 12,032 MMLU-Pro questions across 14 subjects, using DeepSeek-v3.2 with deterministic decoding in a zero-shot setting, Reinforcement Inference improves accuracy from 60.72% to 84.03%.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern large language models (LLMs) are often evaluated and deployed under a one-shot, greedy inference protocol, especially in professional settings that require deterministic behavior. This regime can systematically under-estimate a fixed model's true capability: many errors arise not from missing knowledge, but from premature commitment under internal ambiguity. We introduce Reinforcement Inference, an entropy-aware inference-time control strategy that uses the model's own uncertainty to selectively invoke a second, more deliberate reasoning attempt, enabling stronger performance without any retraining. On 12,032 MMLU-Pro questions across 14 subjects, using DeepSeek-v3.2 with deterministic decoding in a zero-shot setting, Reinforcement Inference improves accuracy from 60.72% to 84.03%, while only incurring 61.06% additional inference calls. A 100% re-asking ablation reaches 84.35%, indicating that uncertainty-aware selection captures most of the attainable improvement with substantially less compute. Moreover, a prompt-only ablation underperforms the baseline, suggesting that the gains are not explained by generic prompting alone. Beyond providing a practical inference-time upgrade, our results suggest a broader entropy-aware paradigm for measuring and expanding model capability: because modern decoder-based models generate outputs autoregressively, entropy and related confidence measures arise naturally as first-class control signals during generation. The resulting gap between one-pass greedy inference and uncertainty-conditioned deliberation offers a diagnostic lens on an LLM's latent reasoning horizon and motivates future training objectives that explicitly constrain correctness--confidence alignment.

Related papers

• Do Uncertainty Signals Help? A Systematic Study of Uncertainty-Aware Decoding with Rollback Mechanisms [21.868021164923515]
  We study an inference-time strategy that uses uncertainty signals to identify unreliable generation regions and roll back to earlier valid prefixes without retraining the model.<n>Our results show that the complete rollback framework improves over equal-budget restart across the evaluated benchmarks and model settings.
  arXiv  Detail & Related papers  (2026-07-31T05:26:42Z)
• Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning [63.24624171679711]
  Large language model (LLM)-based agents often make suboptimal tool-use decisions.<n>We propose TRUST, which incorporates uncertainty quantification into reward design as a repulsive force for maintaining uncertainty separation.
  arXiv  Detail & Related papers  (2026-06-05T07:08:34Z)
• Confidence-Aware Alignment Makes Reasoning LLMs More Reliable [65.44962502963378]
  We introduce CASPO, a framework that aligns token-level confidence with step-wise logical correctness without training a separate reward model.<n>During inference, we propose Confidence-aware Thought (CaT), which dynamically prunes uncertain reasoning branches with negligible O(V) latency.<n>Experiments across ten benchmarks and multiple model families show that CASPO consistently improves reasoning reliability and inference efficiency.
  arXiv  Detail & Related papers  (2026-05-08T07:08:25Z)
• Uncertainty-Aware Reward Discounting for Mitigating Reward Hacking [0.0]
  Real-world objectives are often uncertain, context-dependent, and internally inconsistent.<n>This mismatch can lead to alignment failures such as reward hacking, over-optimization, and overconfident behavior.<n>We introduce a dual-source uncertainty-aware reward framework that explicitly models both uncertainty in value estimation and uncertainty in human preferences.
  arXiv  Detail & Related papers  (2026-04-29T07:14:01Z)
• LLMs Should Express Uncertainty Explicitly [19.324830531710024]
  We compare two complementary interfaces: a global interface, where the model verbalizes a calibrated confidence score for its final answer, and a local interface, where the model emits an explicit uncertain> marker during reasoning.<n> Verbalized confidence substantially improves calibration, reduces overconfident errors, and yields the strongest overall Adaptive RAG controller.<n> Reasoning-time uncertainty signaling makes previously silent failures visible during generation, improves wrong-answer coverage, and provides an effective high-recall retrieval trigger.
  arXiv  Detail & Related papers  (2026-04-07T01:20:29Z)
• Know What You Know: Metacognitive Entropy Calibration for Verifiable RL Reasoning [31.629261193485053]
  Large reasoning models (LRMs) have emerged as a powerful paradigm for solving complex real-world tasks.<n>Most existing outcome-only RLVR pipelines rely almost exclusively on a binary correctness signal and largely ignore the model's intrinsic uncertainty.<n>We propose EGPO, a metacognitive entropy calibration framework that explicitly integrates intrinsic uncertainty into RLVR for enhancing LRMs.
  arXiv  Detail & Related papers  (2026-02-26T08:40:06Z)
• Uncertainty-aware Generative Recommendation [52.0751022792023]
  Uncertainty-aware Generative Recommendation (UGR) is a unified framework that leverages uncertainty as a critical signal for adaptive optimization.<n>UGR not only yields superior recommendation performance but also fundamentally stabilizes training, preventing the performance degradation often observed in standard methods.
  arXiv  Detail & Related papers  (2026-02-12T08:48:51Z)
• Structured Uncertainty guided Clarification for LLM Agents [126.26213027785813]
  LLM agents extend large language models with tool-calling capabilities, but ambiguous user instructions often lead to incorrect invocations and task failures.<n>We introduce a principled formulation of structured uncertainty over tool-call parameters, modeling joint tool-argument clarification as a POMDP with Expected Value of Perfect Information (EVPI) objective for optimal question selection and aspect-based cost modeling to prevent redundancy.<n>Our SAGE-Agent leverages this structured uncertainty to achieve superior efficiency: increasing coverage on ambiguous tasks by 7-39% while reducing clarification questions by 1.5-2.7$times$ compared to strong prompting and uncertainty-based baselines.
  arXiv  Detail & Related papers  (2025-11-11T21:50:44Z)
• ERGO: Entropy-guided Resetting for Generation Optimization in Multi-turn Language Models [9.509429747913519]
  Large Language Models (LLMs) suffer significant performance degradation in multi-turn conversations when information is presented incrementally.<n>We introduce ERGO, which quantifies internal uncertainty via Shannon entropy over next token distributions.<n> ERGO embraces variability in language and modeling, representing and responding to uncertainty.
  arXiv  Detail & Related papers  (2025-10-15T20:33:08Z)
• Guided Uncertainty Learning Using a Post-Hoc Evidential Meta-Model [3.2116198597240846]
  We introduce GUIDE, a lightweight evidential learning meta-model approach that attaches to a frozen deep learning model and explicitly learns how and when to be uncertain.<n> GUIDE requires no retraining, no architectural modifications, and no manual intermediate-layer selection to the base deep learning model.<n>It consistently outperforms state-of-the-art approaches across diverse benchmarks.
  arXiv  Detail & Related papers  (2025-09-29T09:04:15Z)
• Uncertainty-Driven Reliability: Selective Prediction and Trustworthy Deployment in Modern Machine Learning [1.2183405753834562]
  This thesis investigates how uncertainty estimation can enhance the safety and trustworthiness of machine learning (ML) systems.<n>We first show that a model's training trajectory contains rich uncertainty signals that can be exploited without altering its architecture or loss.<n>We propose a lightweight, post-hoc abstention method that works across tasks, avoids the cost of deep ensembles, and achieves state-of-the-art selective prediction performance.
  arXiv  Detail & Related papers  (2025-08-11T02:33:53Z)
• LoGU: Long-form Generation with Uncertainty Expressions [49.76417603761989]
  We introduce the task of Long-form Generation with Uncertainty(LoGU)<n>We identify two key challenges: Uncertainty Suppression and Uncertainty Misalignment.<n>Our framework adopts a divide-and-conquer strategy, refining uncertainty based on atomic claims.<n>Experiments on three long-form instruction following datasets show that our method significantly improves accuracy, reduces hallucinations, and maintains the comprehensiveness of responses.
  arXiv  Detail & Related papers  (2024-10-18T09:15:35Z)
• Selective Learning: Towards Robust Calibration with Dynamic Regularization [79.92633587914659]
  Miscalibration in deep learning refers to there is a discrepancy between the predicted confidence and performance. We introduce Dynamic Regularization (DReg) which aims to learn what should be learned during training thereby circumventing the confidence adjusting trade-off.
  arXiv  Detail & Related papers  (2024-02-13T11:25:20Z)
• Improving the Reliability of Large Language Models by Leveraging Uncertainty-Aware In-Context Learning [76.98542249776257]
  Large-scale language models often face the challenge of "hallucination" We introduce an uncertainty-aware in-context learning framework to empower the model to enhance or reject its output in response to uncertainty.
  arXiv  Detail & Related papers  (2023-10-07T12:06:53Z)
• Discriminative Jackknife: Quantifying Uncertainty in Deep Learning via Higher-Order Influence Functions [121.10450359856242]
  We develop a frequentist procedure that utilizes influence functions of a model's loss functional to construct a jackknife (or leave-one-out) estimator of predictive confidence intervals. The DJ satisfies (1) and (2), is applicable to a wide range of deep learning models, is easy to implement, and can be applied in a post-hoc fashion without interfering with model training or compromising its accuracy.
  arXiv  Detail & Related papers  (2020-06-29T13:36:52Z)

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.