arXiv:2503. 05641v4 Announce Type: replace-cross Abstract: Combining existing pre-trained LLMs is a promising approach for diverse reasoning tasks.
arXiv:2606. 15453v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) based large language models (LLMs), such as Qwen and DeepSeek, have recently emerged as an effective approach to improving model capacity without proportionally increasing computational cost.
arXiv:2608. 08020v1 Announce Type: new Abstract: Test-time compute scaling is a primary driver of performance in large reasoning models (LRMs), but extreme inefficiency bounds current approaches, shifting the critical question from \emph{how much} compute to spend, to \emph{where} to allocate it.
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.
arXiv:2609.01024v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures scale Large Language Model (LLM) capacity efficiently by activating a sparse subset of experts per token. Howeve...
arXiv:2608.21265v1 Announce Type: new Abstract: Large language models often rely on Chain-of-Thought (CoT) reasoning to solve complex tasks, but verbose reasoning traces introduce substantial inferen...
arXiv:2510. 08647v2 Announce Type: replace-cross Abstract: Recent developments have enabled advanced reasoning in Large Language Models (LLMs) via long Chain-of-Thought (CoT), trading efficiency during inference for performance.
The paper introduces Ban&Pick, a post‑training, plug‑and‑play routing strategy for Sparse Mixture‑of‑Experts large language models. It identifies and reinforces a small group of highly influential experts while dynamically pruning redundant ones, leading to accuracy gains across math, code, and reasoning benchmarks. Experiments on DeepSeek and Qwen3 show notable performance improvements and a 1.25× inference speedup without retraining or architectural changes.
arXiv:2604. 16694v2 Announce Type: replace Abstract: Large reasoning models (LRMs) enhance problem-solving capabilities by generating explicit multi-step chains of thought (CoT) reasoning; however, they incur substantial inference latency and computational overhead.
arXiv:2606. 07720v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable reasoning abilities on mathematical and multi-hop planning tasks.
CacheSpec is an inference optimization framework that transforms Program-of-Thoughts (PoT) style programs into reusable cache objects for large language models. By employing a small model for semantic variable extraction on cache hits and speculative drafting during target-LLM generation, CacheSpec reduces inference latency and improves cache reuse. Experiments on shopping, web, formula, and code QA datasets demonstrate up to 3.1× speedup in latency and 2.8× throughput gains over traditional PoT methods, while maintaining or improving task quality.
arXiv:2605. 22873v2 Announce Type: replace-cross Abstract: Chain-of-thought (CoT) reasoning has become the default strategy for enhancing LLM capabilities, yet its application raises a fundamental question: when is explicit reasoning actually beneficial?