arXiv:2607. 03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.
arXiv:2609.38409v1 Announce Type: new Abstract: Recent progress in large language model reasoning has been driven by benchmarks and reinforcement learning environments with automatically verifiable r...
ConsensusBench is a new dataset that supplies rule‑based process‑level signals for large language model reasoning. It identifies key intermediate conclusions—called Consensus Nodes—by filtering correct trajectories and clustering semantically equivalent statements. By incorporating a process reward derived from these nodes into GRPO‑style reinforcement learning, the authors create ConsensusPR, which reduces reward sparsity and improves performance on benchmarks such as AIME, GSM8K, and MATH‑500.
arXiv:2607. 28457v1 Announce Type: cross Abstract: Scaling test-time computation can improve language-model reasoning, but uniform budgets waste computation on easy inputs, while verifier-guided refinement relies on external feedback.
arXiv:2606. 09052v1 Announce Type: cross Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision.
RGDT-Bench is a new benchmark that evaluates large language models on Rule‑Governed Decision Tasks, where models must apply external rules to facts, justify decisions, and provide checkable justifications. The benchmark offers 202.1K condition‑level supervision slots across four task tracks and eight task‑probe combinations, and it labels warrant completeness through label‑blind extraction and deterministic checks. Evaluation shows that among correct responses, 40.2% of warrants are incomplete, and existing evaluators struggle to detect this, prompting the authors to train a reward model that improves AUROC to 69.24% and outperforms outcome‑supervised baselines.
AutoVerifier is a residual‑guided, non‑parametric optimization framework designed to improve reference‑based answer verification. It learns verifier inductive biases from recurring errors, records them as rule cards, and promotes them to code modules or prompt guidance only after replay validation ensures no regressions. Experiments on four verifier benchmarks show that AutoVerifier surpasses state‑of‑the‑art verifiers by a large margin.