Tag
提出SWEAR框架，通过自评难度分数与分阶段强化学习为大型音频语言模型动态分配推理算力，在MMAU-test-mini和MMAR上以更少的生成token实现了更高的准确率。
The paper proposes adaptive reasoning in agentic AI systems to dynamically allocate computational effort based on task demands, avoiding over-reasoning and under-reasoning through evaluation on MATH-500 and GAIA benchmarks.
Introduces SuCo, a two-stage training framework for Large Reasoning Models that uses the concept of Minimal Sufficient CoT to reduce reasoning tokens while improving accuracy across math, code, and science benchmarks.
A new 30B model matches systems 20-30x its size on popular benchmarks while using up to 95% fewer reasoning tokens than comparable agentic LLMs, achieved through a learned configurator that decides when and how to reason. Model and code are openly available.
New research introduces SR²AM, a configurator that self-regulates when to use simulative reasoning, improving efficiency and performance in LLMs.
This paper introduces Conditional Entropy Shaping (CES), a framework that dynamically controls token-level response entropy in LLMs to balance reasoning depth and conciseness, achieving improved accuracy while reducing response length on mathematical benchmarks.
LEAD dynamically adapts reasoning efficiency during training by using online calibration of correctness-efficiency trade-offs and adaptive problem-specific length targets, improving mathematical reasoning accuracy and reducing output length.
Researchers introduce x1, a family of reasoning models that adaptively select optimal languages for reasoning on a per-instance basis, demonstrating that language choice impacts reasoning quality in multilingual and cultural tasks.