TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement

• URL: http://arxiv.org/abs/2603.03297v1
• Date: Fri, 06 Feb 2026 18:55:40 GMT
• Title: TTSR: Test-Time Self-Reflection for Continual Reasoning Improvement
• Abstract summary: Test-time Training enables model adaptation using only test questions.<n>We propose textbfTTSR, a self-reflective test-time self-evolving training framework.
• Score: 7.122068644799895
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Test-time Training enables model adaptation using only test questions and offers a promising paradigm for improving the reasoning ability of large language models (LLMs). However, it faces two major challenges: test questions are often highly difficult, making self-generated pseudo-labels unreliable, and existing methods lack effective mechanisms to adapt to a model's specific reasoning weaknesses, leading to inefficient learning. To address these issues, we propose \textbf{TTSR}, a self-reflective test-time self-evolving training framework. TTSR employs a single pretrained language model that alternates between the roles of a \textit{Student} and a \textit{Teacher} at test time. The Student focuses on solving problems and learning from synthesized variant questions, while the Teacher analyzes the Student's failed reasoning trajectories, summarizes recurring reasoning weaknesses, and synthesizes targeted variant questions accordingly. This process guides the model to improve within a learnable regime through a continual self-evolving loop. Experimental results on multiple challenging mathematical reasoning benchmarks show that TTSR consistently improves reasoning performance and generalizes well across different model backbones and general-domain reasoning tasks. These findings suggest that teacher-mediated self-reflection provides an effective pathway for stable and continual reasoning improvement at test time.

Related papers

• A Survey on Self-Improving Test-Time Intelligence: Feedback-Driven Adapting, Learning, and Scaling at Inference [72.19201465132619]
  We present feedback-driven Test-Time Intelligence (TTI) as a unified perspective for understanding such deployment-time improvement.<n>We use this view to relate test-time adaptation, test-time learning, and test-time scaling, highlighting both their distinctions and their growing overlap in hybrid systems.<n>Our goal is to provide a coherent foundation and research roadmap for the study of self-improving AI systems at test time.
  arXiv  Detail & Related papers  (2026-09-01T11:41:39Z)
• TTCS: Test-Time Curriculum Synthesis for Self-Evolving [47.826209735956716]
  Test-Time Training offers a promising way to improve the reasoning ability of large language models.<n>We propose TTCS, a co-evolving test-time training framework.<n>We show that TTCS consistently strengthens the reasoning ability on challenging mathematical benchmarks.
  arXiv  Detail & Related papers  (2026-01-30T06:38:02Z)
• Counterfactual Self-Questioning for Stable Policy Optimization in Language Models [0.0]
  We propose Counterfactual Self-Questioning, a framework in which a single language model generates and evaluates counterfactual critiques of its own reasoning.<n> Experiments on multiple mathematical reasoning benchmarks show that counterfactual self-questioning improves accuracy and training stability, particularly for smaller models.
  arXiv  Detail & Related papers  (2025-12-31T09:10:37Z)
• Stabilizing Reinforcement Learning for Honesty Alignment in Language Models on Deductive Reasoning [27.42733470720954]
  We propose a reinforcement learning method that injects ground truth trajectories into rollouts, preventing early training collapse.<n>Our results demonstrate that this method stabilizes learning and significantly improves the overall reasoning performance.
  arXiv  Detail & Related papers  (2025-11-12T11:34:19Z)
• Learning to Make MISTAKEs: Modeling Incorrect Student Thinking And Key Errors [58.65143578052761]
  This paper presents a new method, MISTAKE, that constructs high-quality synthetic examples of reasoning errors.<n>We evaluate MISTAKE on three educational tasks and find that it results in (1) higher accuracy when simulating incorrect student answers.
  arXiv  Detail & Related papers  (2025-10-13T15:10:38Z)
• Boosting Process-Correct CoT Reasoning by Modeling Solvability of Multiple-Choice QA [10.122669382758122]
  We show that when questions are effectively unsolvable for a model, spurious chains of thought (CoTs) are more likely to appear.<n>We adapt outcome-supervised reward models and reinforcement learning with group-relative advantage to incorporate solvability into their objectives.<n>Our results highlight solvability as a key factor for reducing hallucinations and increasing reliability in CoT reasoning.
  arXiv  Detail & Related papers  (2025-09-30T08:34:16Z)
• Learning to Refine: Self-Refinement of Parallel Reasoning in LLMs [102.48588475875749]
  We introduce Generative Self-Refinement (GSR), a novel parallel test-time scaling framework.<n>GSR generates a set of candidate responses in parallel and then performs self-refinement to synthesize a new superior solution.<n>We show that our method achieves state-of-the-art performance across five mathematical benchmarks.
  arXiv  Detail & Related papers  (2025-08-27T06:51:48Z)
• ReVISE: Learning to Refine at Test-Time via Intrinsic Self-Verification [53.80183105328448]
  Refine via Intrinsic Self-Verification (ReVISE) is an efficient framework that enables LLMs to self-correct their outputs through self-verification.<n>Our experiments on various reasoning tasks demonstrate that ReVISE achieves efficient self-correction and significantly improves reasoning performance.
  arXiv  Detail & Related papers  (2025-02-20T13:50:02Z)
• Enhancing LLM Reasoning via Critique Models with Test-Time and Training-Time Supervision [120.40788744292739]
  We propose a two-player paradigm that separates the roles of reasoning and critique models. We first propose AutoMathCritique, an automated and scalable framework for collecting critique data. We demonstrate that the critique models consistently improve the actor's performance on difficult queries at test-time.
  arXiv  Detail & Related papers  (2024-11-25T17:11:54Z)

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.