arXiv:2605. 17609v2 Announce Type: replace Abstract: Many inference-time language-model pipelines combine a cheap reward signal with an expensive verifier, such as exact answer checking in mathematical reasoning or hidden-test execution in code generation.
arXiv:2606. 05464v1 Announce Type: new Abstract: Verifiable reward training has improved mathematical and coding reasoning, but these domains capture only part of step-by-step decision making.
arXiv:2602.13551v3 Announce Type: replace Abstract: Reward models (RMs) play a central role throughout the language model (LM) pipeline, particularly in non-verifiable domains. However, the dominant...
The paper introduces probe-driven test-time reinforcement learning (TTRL) for code generation, using probe inputs derived from problem statements to evaluate candidate programs and define a Probe Consensus Reward (PCR). To address PCR’s unreliability and prevent reward hacking, the authors propose Entropy-Regularized Rank-Masked Policy Optimization (ERPO), which applies rank masking and an entropy ceiling to produce conservative policy updates. Experiments on coding benchmarks show that ERPO significantly improves pass@1 and pass@k metrics in both in-domain adaptation and zero-shot transfer scenarios.
The paper introduces APIVIS, a training-time framework that integrates finite-budget Gumbel search into reinforcement learning with verifiable rewards (RLVR) for mathematical reasoning. APIVIS combines direct and searched responses within each rollout group, uses selective supervision on search-improved tokens, and applies value-guided selection to improve verifier rewards at each searched state. Experiments on standard mathematical reasoning benchmarks and various model scales show significant performance gains over existing search-based methods.
arXiv:2608. 09217v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central post-training paradigm for eliciting reasoning capabilities in large language models, yet uniform task sampling allocates compute without regard to differences in how tasks respond to optimization.
arXiv:2609.38672v1 Announce Type: cross Abstract: Beam-search-based test-time methods provide an effective way to improve large language model (LLM) performance on long-horizon generation by pruning...
arXiv:2606. 25451v1 Announce Type: new Abstract: Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive.
arXiv:2609.37119v1 Announce Type: cross Abstract: Recent approaches to reinforcement learning (RL) post-training for large language models increasingly remove the critic to reduce training instabilit...
arXiv:2608. 16072v1 Announce Type: cross Abstract: Reinforcement learning (RL) with group-relative advantages has become the de facto standard for post-training language model reasoners.
arXiv:2608.23566v2 Announce Type: replace-cross Abstract: Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling multiple responses for...
The paper introduces Best‑Practice Critic Optimization (BPCO), a stable and efficient recipe for training a critic in reinforcement learning for large language models. BPCO combines DPPO, bounded value predictions, Monte Carlo targets, unnormalized policy advantages, and length‑adaptive advantage estimation, allowing the critic to be conditioned on hidden reward information. Experiments on mathematical reasoning tasks with models from 1.5B to 30B parameters show that BPCO consistently outperforms a strong critic‑based baseline and matches or exceeds group‑based methods while sampling only one response per prompt.
arXiv:2609.16660v1 Announce Type: new Abstract: Test-time reinforcement learning adapts a model on its own unlabeled test set using majority-vote pseudo-labels and has shown strong results in mathema...