TTPO: Test-Time Policy Optimization

• URL: http://arxiv.org/abs/2608.27448v1
• Date: Thu, 27 Aug 2026 17:58:10 GMT
• Title: TTPO: Test-Time Policy Optimization
• Abstract summary: Test-Time Policy Optimization (TTPO) is an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL.<n>We show that TTPO matches label-supervised OPSD on five competition-level benchmarks, raises Qwen3-1.7B from 38.0% to 45.2% in TTT, yields +25.2% to +36.4% without thinking, and shows strong cross-task generalization.
• Score: 53.81524570216593
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent prominent post-training methods, such as Reinforcement Learning (RL) and On-Policy Self-Distillation (OPSD), have driven rapid progress in mathematical reasoning for large language models, yet their reliance on ground-truth labels precludes test-time training (TTT). Replacing ground truth with majority-vote pseudo-labels is a natural alternative, yet it is fragile: an incorrect vote corrupts the teacher and misleads every token. We observe that this failure mode is asymmetric: rollouts that disagree with the pseudo-label are typically wrong regardless of whether the vote itself is correct. Building on this observation, we propose Test-Time Policy Optimization (TTPO), an asymmetric objective that distills agreeing rollouts via OPSD and penalizes disagreeing rollouts with Grouped RL. Token-level selection further refines both branches: distillation down-weights already-converged positions, while RL penalizes only confident errors. Both updates remain well-grounded even under frequent pseudo-label errors, and majority-vote routing yields tighter self-supervision as the model improves. Without any labels, TTPO matches label-supervised OPSD on five competition-level benchmarks, raises Qwen3-1.7B from 38.0% to 45.2% in TTT, yields +25.2% to +36.4% without thinking, and shows strong cross-task generalization.

Related papers

• CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning [6.071121358322323]
  emphCoRE improves the untrained base by $+21.7$ points on average versus $+20.4$ for majority-vote TTRL.<n>Treating the roll-out group as a graph rather than a ballot box turns a brittle vote into a calibrated, graded, self-supervised reward at no extra roll-out cost.
  arXiv  Detail & Related papers  (2026-08-10T09:06:03Z)
• Detecting and Mitigating the Correct-Answer Extinction Window in Test-Time Reinforcement Learning with Majority Voting [4.336665585098371]
  Test-time reinforcement learning (TTRL) reports substantial accuracy gains on mathematical reasoning benchmarks using majority vote as a pseudo-label signal.<n>We propose TTRL-Guard, a lightweight framework with three mechanisms targeting the textitCorrect-Answer Extinction Window<n>Experiments across three models and four benchmarks show that TTRL-Guard achieves the best average pass@1 on Qwen2.5-7B-Instruct and Qwen3-4B, improves relatively over TTRL by +54% on AIME 2025.
  arXiv  Detail & Related papers  (2026-05-19T06:58:44Z)
• CEPO: RLVR Self-Distillation using Contrastive Evidence Policy Optimization [50.59956036193097]
  A model produces a correct solution under reinforcement learning with verifiable rewards (RLVR)<n>Every token receives the same reward signal regardless of whether it was a decisive reasoning step or a grammatical filler.<n>We propose Contrastive Evidence Policy Optimization (CEPO)<n>CEPO asks a sharper question at every token: "does the correct answer favor this token?" but "does the correct answer favor it while the wrong answer disfavors it?"
  arXiv  Detail & Related papers  (2026-05-19T06:46:19Z)
• Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning [8.024041325202612]
  Chain-of-thought (CoT) reasoning with self-consistency improves performance by aggregating multiple sampled reasoning paths.<n>We introduce a conformal procedure for CoT reasoning that directly addresses aggregation uncertainty.<n>Our approach replaces majority voting with weighted score aggregation over reasoning paths and calibrates an abstention rule using conformal risk control.
  arXiv  Detail & Related papers  (2026-05-13T20:33:59Z)
• TEMPO: Scaling Test-time Training for Large Reasoning Models [87.61789183311856]
  Test-time training (TTT) adapts model parameters on unlabeled test instances during inference time.<n>We propose TEMPO, a TTT framework that interleaves policy refinement on unlabeled questions with periodic critic recalibration on a labeled dataset.
  arXiv  Detail & Related papers  (2026-04-21T10:01:04Z)
• What If Consensus Lies? Selective-Complementary Reinforcement Learning at Test Time [57.533031432715084]
  Test-Time Reinforcement Learning (TTRL) enables Large Language Models (LLMs) to enhance reasoning capabilities on unlabeled test streams.<n>Existing TTRL methods rely exclusively on positive pseudo-labeling strategies.<n>We propose SCRL, a robust test-time reinforcement learning framework that effectively mitigates label noise amplification.
  arXiv  Detail & Related papers  (2026-03-20T11:47:12Z)
• CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution [52.691495954442985]
  CoVerRL is a framework where a single model alternates between generator and verifier roles, with each capability bootstrapping the other.<n> Experiments across Qwen and Llama model families demonstrate that CoVerRL outperforms label-free baselines by 4.7-5.9% on mathematical reasoning benchmarks.<n>Self-verification accuracy improves from around 55% to over 85%, confirming that both capabilities genuinely co-evolve.
  arXiv  Detail & Related papers  (2026-03-18T14:38:55Z)
• RESTRAIN: From Spurious Votes to Signals -- Self-Driven RL with Self-Penalization [52.01526898310723]
  We introduce RESTRAIN, a self-penalizing RL framework that converts the absence of gold labels into a useful learning signal.<n>Instead of overcommitting to spurious majority votes, RESTRAIN exploits signals from the model's entire answer distribution.<n>On challenging reasoning benchmarks, RESTRAIN delivers large gains using only unlabeled data.
  arXiv  Detail & Related papers  (2025-10-02T16:24:01Z)

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.