The paper introduces Uncertainty-Aware Budget Allocation (UAB), a concave integer optimization framework that reallocates a fixed sampling budget for language model reasoning based on uncertainty estimated from initial samples. In Phase‑1, each question receives a small number of generations, and the disagreement among these answers (vote entropy) signals difficulty. Phase‑2 uses a marginal‑greedy algorithm to allocate the remaining budget, focusing on questions with high initial disagreement, leading to a 2.3% average accuracy improvement over uniform allocation across five open‑weight models and five reasoning benchmarks, with up to 5.5% gains on individual benchmarks, especially in low‑resource settings.
arXiv:2608. 07968v1 Announce Type: cross Abstract: Reasoning language models increasingly use test-time compute to improve performance, but existing evaluations typically study this compute one question at a time.
The paper introduces Uncertainty-Aware Allocation (UAA), a training‑free framework that adjusts the per‑step budget in large language model tree search based on sibling action dispersion. By estimating uncertainty from sibling dispersion, UAA decouples value from uncertainty, allowing selective expansion and pruning. Experiments on mathematical reasoning, logical reasoning, and planning tasks show that UAA can cut token usage by up to 90% and latency by up to 9× while maintaining comparable accuracy across multiple tree search algorithms and both open‑ and closed‑source LLMs.
arXiv:2610.17679v1 Announce Type: cross Abstract: Chain-of-thought (CoT) improves reasoning but incurs substantial autoregressive rationale cost. Continuous CoT moves intermediate computation into re...
arXiv:2601.03822v2 Announce Type: replace Abstract: Large language models (LLMs) can achieve strong reasoning performance with sufficient computation, but they do not inherently know how much computa...
arXiv:2606. 03092v1 Announce Type: new Abstract: Inference-time scaling has emerged as a critical avenue for enhancing Large Language Models' performance, yet real-world deployment is constrained by strict computational budgets.
The paper introduces Budget‑Efficient Thinking (BET), a two‑stage framework that treats adaptive reasoning as a computational investment, aligning solve‑or‑fold decisions with expected return rather than perceived difficulty. BET learns three distinct behaviors: concise short solves for easy queries, early abstention (nice fold) when further reasoning is unlikely to pay off, and allocating sufficient compute (hero call) for hard‑but‑solvable questions. Experiments on seven benchmarks with three base models show BET cuts reasoning tokens by 54% while boosting accuracy by up to 3.2%, and it transfers effectively to scientific QA and logical reasoning tasks.
arXiv:2606. 13982v1 Announce Type: cross Abstract: Sampling plays an important role in long-form language-model reasoning.
The paper introduces BudgetAPO, a single‑stage prompt optimizer designed for tight‑budget scenarios where only a few hundred model calls are feasible. BudgetAPO adapts the evaluation slice size to each task’s noise level, uses a fixed slice to turn accept/reject decisions into paired comparisons, and applies a reflective operator to jointly rewrite reasoning strategy and output format. Across seven benchmarks and five subject models, BudgetAPO outperforms existing methods, ranking first on every subject and requiring far fewer calls to achieve comparable or superior performance.
arXiv:2604. 17267v2 Announce Type: replace Abstract: Large Language Models can generate synthetic survey responses at low cost, but their accuracy varies unpredictably across questions.
arXiv:2510.27042v3 Announce Type: replace Abstract: Increasing the thinking budget of AI models can significantly improve accuracy, but not all questions warrant the same amount of reasoning. Users m...
arXiv:2606. 11164v1 Announce Type: new Abstract: Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache growth.
GAMMA is a post‑training framework that learns module‑wise precision preferences for mixed‑precision quantization of large language models. It optimizes a teacher‑forced hidden‑state reconstruction objective under an augmented Lagrangian constraint and then projects the learned preferences into exact budget‑feasible discrete assignments via integer programming. Because the learned preferences encode a stable sensitivity ranking, a single training run can be reused for any deployment budget, reducing per‑budget adaptation from hours to minutes and outperforming fixed‑precision baselines and search‑based methods on Llama and Qwen models.