Self-consistency (SC) is a widely used decoding strategy for improving chain-of-thought reasoning, but it requires sampling many complete reasoning trajectories with a preset budget. Its efficient var...
Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks. However, standard approaches such as independent sampling and sequential multi-turn refinement operate without token-level credit assignment, resulting in computational inefficiency, since valid reasoning prefixes are frequently discarded.
arXiv:2607. 21453v1 Announce Type: new Abstract: Scaling inference-time computation has emerged as a reliable method to improve the performance of large language models on complex reasoning and programming tasks.
arXiv:2511. 12309v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a widely used test-time inference technique for improving performance in chain-of-thought reasoning.
arXiv:2611.06606v1 Announce Type: new Abstract: Large language models can solve many multi-step reasoning problems, but their reasoning remains brittle: plausible intermediate steps often lead to inc...
arXiv:2604. 17433v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a popular technique for improving the reasoning accuracy of large language models by aggregating multiple sampled outputs, but it comes at a high computational cost due to extensive sampling.
arXiv:2608. 10928v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) improve performance by allocating additional inference-time compute to generate extended chain-of-thought reasoning.
arXiv:2608. 05643v1 Announce Type: new Abstract: Test-time scaling improves LLM reasoning by using additional inference compute, but wider sampling alone can suffer from diminishing returns: new rollouts often repeat existing answer patterns instead of adding useful reasoning diversity.
arXiv:2505. 12992v4 Announce Type: replace-cross Abstract: Inference-time scaling techniques have significantly bolstered the reasoning capabilities of large language models (LLMs) by harnessing additional computational effort at inference without retraining.
ThinkFuse is a training‑free test‑time fusion framework designed for small reasoning models (SRMs). It selectively intervenes in unreliable reasoning segments by comparing segment‑level uncertainty shifts with trajectory‑level uncertainty trends, and fuses auxiliary reasoning paths into the primary model’s trajectory. Experiments show ThinkFuse outperforms baselines on mathematical and knowledge‑intensive benchmarks, requires fewer fusion triggers, and generates fewer tokens, demonstrating efficient selective triggering.
The paper introduces Planned Test-Time Scaling (PTTS), a method that replaces independent sampling of reasoning branches with a coordinated joint policy. PTTS uses a planner to generate distinct solution outlines for each branch and an executor to produce full solutions, thereby improving coverage of complementary reasoning modes. Two variants—PTTS‑ZS (zero‑shot) and PTTS‑RL (reinforcement‑learned)—demonstrate significant gains on five mathematical reasoning benchmarks, with PTTS‑RL achieving up to a 13.4‑point improvement in pass@64 over repeated sampling.
arXiv:2608. 15065v1 Announce Type: new Abstract: Large Reasoning Models produce diverse, sometimes inconsistent answers across repeated queries on the same problem, so multi-sample inference is a prerequisite for reliable deployment.