CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning

• URL: http://arxiv.org/abs/2608.09324v1
• Date: Mon, 10 Aug 2026 09:06:03 GMT
• Title: CoRE: Consensus Rewards via Equilibrium for Test-Time Reinforcement Learning
• Abstract summary: 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.
• Score: 6.071121358322323
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: On unlabeled test data, reinforcement learning lacks a ground-truth reward; test-time RL methods derive one from the model's own roll-outs, rewarding those that match the majority vote over $N$ sampled answers. That vote discards a correct answer whenever it is a minority and scores every majority-matching roll-out identically. We replace it with \emph{CoRE} (Consensus Rewards via Equilibrium): the $N$ roll-outs form a graph whose edges combine answer agreement, reasoning similarity, and generation confidence, and replicator dynamics extract its dominant set, yielding a refined pseudo-label, a graded per-roll-out reward, and a per-question cohesiveness gate. CoRE strictly generalizes voting: majority voting is recovered as a special case; a block-value analysis gives a sharp threshold for when consensus recovers a correct minority against a larger wrong plurality; and confidence calibration provably lowers that threshold multiplicatively. Across seven backbones and five benchmarks (42 model--benchmark cells, three seeds each), \emph{CoRE} improves the untrained base by $+21.7$ points on average versus $+20.4$ for majority-vote TTRL, wins wherever agreement is contestable with margins over the vote of up to $+7.5$ points, and reaches the voting baseline's plateau accuracy in $54$--$70$\% fewer steps. Consensus, not counting: 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.

Related papers

• TTPO: Test-Time Policy Optimization [53.81524570216593]
  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.
  arXiv  Detail & Related papers  (2026-08-27T17:58:10Z)
• Rubric Dropout: A Simple Way to Mitigate Reward Hacking in Rubric-as-Reward RL [11.857468467125505]
  We find that the two scores diverge during training.<n>A judge with a fixed bias would shift the gold curve by a constant, not send it down while the training score rises.<n>We propose Dropout, a one-line fix borrowed from neuron dropout.
  arXiv  Detail & Related papers  (2026-08-12T05:29:21Z)
• Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short [51.667769734342635]
  Reinforcement learning with verifiable rewards (RLVR) has become a leading paradigm for improving the reasoning ability of large language models.<n>We propose Reasoning Arena, an adaptive training framework that routes such non-diverse reward groups to a judge system instead of discarding them.<n>We show that Reasoning Arena consistently outperforms the RLVR baseline by 7.6% on average in competition mathematics and coding benchmarks.
  arXiv  Detail & Related papers  (2026-06-08T11:57:17Z)
• A Pre-Registered Causal Partition of Self-Consistency Elicitation and Reward Design in RLVR [1.2958054117511815]
  Reinforcement learning from rewards improves reasoning even when the reward signal is spurious.<n> Practitioners commonly interpret naive = acc(TRUE) - acc(R) as the reward-design effect.<n>We prove this estimand is systematically biased.
  arXiv  Detail & Related papers  (2026-06-04T09:35:54Z)
• Step-wise Rubric Rewards for LLM Reasoning [72.17879367869503]
  Reinforcement Learning with Verifiable Rewards (RLVR) is widely used to improve reasoning in large language models.<n>We find 18.2% of steps in correct responses are wrong yet positively rewarded.<n>Across six mathematical reasoning benchmarks, SRaR improves average accuracy over RaR by 3.57 points.
  arXiv  Detail & Related papers  (2026-05-17T07:08:14Z)
• 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)
• JURY-RL: Votes Propose, Proofs Dispose for Label-Free RLVR [39.03968285406107]
  JURY-RL is a label-free RLVR framework that decouples answer proposal from reward disposal.<n>It consistently outperforms other label-free baselines on mathematical reasoning benchmarks.<n>It attains pass@1 performance comparable to supervised ground-truth training.
  arXiv  Detail & Related papers  (2026-04-28T09:29:00Z)
• CARE What Fails: Contrastive Anchored-REflection for Verifiable Multimodal [84.71254539482369]
  Group-relative reinforcement learning with verifiable rewards (RLVR) often wastes the most informative data it already has the failures.<n>We present CARE, a failure-centric post-training framework for multimodal reasoning that turns errors into supervision.<n> CARE improves accuracy and training smoothness while explicitly increasing the share of learning signal that comes from failures.
  arXiv  Detail & Related papers  (2025-12-22T16:34:21Z)
• Reinforcement Learning with Verifiable yet Noisy Rewards under Imperfect Verifiers [90.50039419576807]
  Reinforcement Learning with Verifiable Rewards (RLVR) trains policies against automated verifiers to avoid costly human labeling.<n>To reduce vulnerability to verifier hacking, many RLVR systems collapse rewards to binary $0,1$ during training.<n>This choice carries a cost: it introduces textitfalse negatives (rejecting correct answers, FNs) and textitfalse positives (accepting incorrect ones, FPs)
  arXiv  Detail & Related papers  (2025-10-01T13:56:44Z)
• Compute as Teacher: Turning Inference Compute Into Reference-Free Supervision [26.922922043969958]
  We propose turning exploration into supervision through Compute as Teacher (CaT)<n>CaT synthesizes a single reference from a group of parallel rollouts and then optimizing toward it.<n>As a test-time procedure, CaT improves Gemma 3 4B, Qwen 3 4B, and Llama 3.1 8B.
  arXiv  Detail & Related papers  (2025-09-17T17:59:42Z)
• The Majority is not always right: RL training for solution aggregation [53.1050856072799]
  We train an aggregator model to review, reconcile, and synthesize a final, correct answer.<n>A key ingredient is careful balancing of easy and hard training examples.<n>We find our method, AggLM, outperforms both strong rule-based and reward-model baselines.
  arXiv  Detail & Related papers  (2025-09-08T16:39:38Z)

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.