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.
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:2510. 22228v2 Announce Type: replace-cross Abstract: Layer pruning has emerged as a widely adopted technique for improving the efficiency of large language models (LLMs).
The paper introduces SWE-Flux, a repository‑level benchmark designed to test large language models’ ability to reason about runtime behavior. It contains 480 execution‑grounded instances from 12 real Python repositories, with gold answers automatically harvested from instrumented test executions. Evaluation of five LLMs shows the task remains difficult, with the best model achieving only 37% accuracy, and the benchmark can generate challenging variants through input perturbation.
arXiv:2608. 04001v1 Announce Type: cross Abstract: Large language models can solve substantially harder reasoning problems with more inference-time compute.
arXiv:2606. 08976v1 Announce Type: new Abstract: LLM-based RTL generation and reasoning is a promising direction for hardware design automation.
arXiv:2608. 07424v1 Announce Type: new Abstract: Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a stronger evaluator.
The paper surveys efficient reasoning in large language models, contrasting fast intuitive (System 1) and slow deep (System 2) reasoning. It analyzes why System 2 is computationally costly yet more accurate, and why System 1 is efficient but less effective. The survey covers causes of inefficiency, patterns of reasoning behavior, and potential solutions to balance performance and computational budgets, offering actionable insights and an open‑source repository for ongoing research.
InternBootcamp is an open‑source framework that offers over 1,000 domain‑diverse task environments for large language model (LLM) reasoning research. It introduces Bootcamp‑Eval, an automatically generated benchmark for comprehensive performance assessment. Experiments show that training on InternBootcamp significantly improves reasoning performance, with a 32B model achieving state‑of‑the‑art results on Bootcamp‑Eval and other established benchmarks, demonstrating that scaling the number of training tasks yields consistent gains.
Parason is a new framework that discovers and exploits both subtask and trial parallelism in large language model (LLM) reasoning. By converting sequential reasoning traces into structured parallel trajectories and training with Parallelism-Aware Group Relative Policy Optimization, it balances accuracy, latency, and parallelism. Experiments on mathematical reasoning benchmarks such as AIME24 and AIME25 show that Parason achieves an average acceleration of about 1.7× while maintaining competitive accuracy.
arXiv:2606. 06915v1 Announce Type: cross Abstract: Test-time compute (TTC) scaling has emerged as a powerful paradigm for improving large language model (LLM) reasoning by allocating additional compute during inference, e.
PetriBench is a compact, fully self‑contained, and scalable benchmark that evaluates large language model (LLM) reasoning over dynamic state spaces using Petri nets. It organizes reasoning into four task families with Easy, Medium, and Hard levels, each generated by increasing structural complexity and evaluated against exact ground truth. Experiments across proprietary and open‑weight models show that accuracy consistently drops with difficulty, revealing distinct task‑specific capability profiles, while test‑time compute and procedural generation affect performance differently across tasks.