Large Reasoning Models (LRMs) generate long reasoning traces that expose intermediate inference behavior, offering opportunities to study and control reasoning in AI coding. However, the underlying pa...
arXiv:2605.11388v2 Announce Type: replace Abstract: Humans intuitively solve complex problems by flexibly shifting among reasoning modes: they plan, execute, revise intermediate goals, resolve ambigu...
TRACES (Tagging Reasoning Steps for Adaptive Cost‑Efficient Early‑Stopping) is a lightweight framework that tags reasoning steps of large‑language models in real time, enabling adaptive, cost‑efficient early stopping during inference. By monitoring the types of steps generated, the method identifies when models shift their reasoning after arriving at a correct answer, allowing for interpretable stopping criteria. Experiments on mathematical reasoning benchmarks (MATH500, GSM8K, AIME) and knowledge benchmarks (MMLU, GPQA) show token reductions of 20–50% while preserving accuracy, with more conservative thresholds needed for harder tasks such as BeyondAIME and IMO AnswerBench.
The paper introduces a method to control reasoning behaviors in Mixture-of-Experts (MoE) language models by labeling sentence-level segments with six distinct reasoning behaviors (planning, execution, restatement, fact, reflection, and conclusion). Linear probes on MoE router logits can predict these behaviors nearly as accurately as probes on the full hidden state, enabling the authors to edit router scores during inference to reduce overthinking. This intervention cuts generated tokens by a median of 30.4% (up to 63.3%) across multiple models and benchmarks without significant loss in accuracy, and often improves it.
arXiv:2604. 04930v2 Announce Type: replace-cross Abstract: Large reasoning models rely on long chain-of-thought generation to solve complex problems, but extended reasoning often incurs substantial computational cost and can even degrade performance due to overthinking.
arXiv:2604.15490v2 Announce Type: replace Abstract: Recent developments in reasoning capabilities have enabled large language models to solve increasingly complex mathematical, symbolic, and logical...
The paper argues that large language models need adaptive reasoning rather than fixed reasoning budgets. It shows that over‑reasoning leads to high computational cost without accuracy gains, while under‑reasoning results in incorrect or incomplete solutions. The authors evaluate these failure modes on MATH‑500 and the GAIA benchmark, highlighting the need for dynamic reasoning allocation in agentic AI systems.
arXiv:2604. 01161v2 Announce Type: replace Abstract: Large language models (LLMs) exhibiting test-time scaling behavior, such as extended reasoning traces and self-verification, have demonstrated remarkable performance on complex, long-term reasoning tasks.
The paper introduces CodeRQ-Bench, the first benchmark for assessing large language model reasoning quality across coding tasks such as generation, summarization, and classification. It analyzes over a thousand mismatches from existing evaluators, identifies recurring limitations, and derives design insights that lead to a new two‑stage evaluator, VERA. Experiments show VERA outperforms strong baselines, improving AUCROC by up to 0.26 and AUPRC by up to 0.21 on four datasets.
arXiv:2606. 16934v1 Announce Type: cross Abstract: Reasoning with a Code Interpreter (CI) has emerged as an effective paradigm for enhancing the reasoning capabilities of large language models (LLMs) through executable computation and iterative verification.
arXiv:2605. 28742v2 Announce Type: replace Abstract: Language models can use verifiable rewards to improve at a wide variety of reasoning tasks.
The paper investigates how explicit reasoning in language models can lead to a "reasoning‑trace overflow," where the model spends most of its 32k‑token output budget on reasoning rather than producing code. Across seven models and six code benchmarks, overflow is rare on simple tasks but common on harder benchmarks, often due to repetitive reasoning loops. The study shows that disabling reasoning can sometimes be competitive, while prompt steering and budgeted transitions can mitigate overflow and improve token efficiency.