Pith. sign in

REVIEW 6 cited by

Evolving Deeper LLM Thinking

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2501.09891 v1 pith:ELG3LBCX submitted 2025-01-17 cs.AI

Kuang-Huei Lee , Ian Fischer , Yueh-Hua Wu , Dave Marwood , Shumeet Baluja , Dale Schuurmans , Xinyun Chen This is my paper
classification cs.AI
keywords inferenceevolutionlanguagemindapproachnaturalproblemproposed
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We explore an evolutionary search strategy for scaling inference time compute in Large Language Models. The proposed approach, Mind Evolution, uses a language model to generate, recombine and refine candidate responses. The proposed approach avoids the need to formalize the underlying inference problem whenever a solution evaluator is available. Controlling for inference cost, we find that Mind Evolution significantly outperforms other inference strategies such as Best-of-N and Sequential Revision in natural language planning tasks. In the TravelPlanner and Natural Plan benchmarks, Mind Evolution solves more than 98% of the problem instances using Gemini 1.5 Pro without the use of a formal solver.

Discussion (0). Sign in to comment.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Cognitive Alpha Mining via LLM-Driven Code-Based Evolution

    cs.CL 2025-11 unverdicted novelty 7.0 of 10

    CogAlpha combines LLM reasoning with code-level evolutionary search to discover financial alphas that show higher predictive accuracy and generalization than prior methods on five stock datasets.

  2. Procedural Knowledge at Scale Improves Reasoning

    cs.CL 2026-04 unverdicted novelty 6.0 of 10

    Retrieving compact procedural hints from 32M subquestion–subroutine pairs improves reasoning-model accuracy on math, science, and coding benchmarks beyond compute-matched test-time scaling.

  3. CUDA-L1: Improving CUDA Optimization via Contrastive Reinforcement Learning

    cs.AI 2025-07 conditional novelty 6.0 of 10

    A contrastive reinforcement learning framework, CUDA-L1, trains an LLM to optimize CUDA kernels and reports 3.12x average speedup on KernelBench, though evaluation is on the same tasks used for training.

  4. Deep Researcher with Test-Time Diffusion

    cs.CL 2025-07 conditional novelty 5.0 of 10

    A test-time 'denoising' loop that repeatedly revises a draft report using fresh web retrieval, plus a component-wise self-evolution step, beats existing deep research agents on several benchmarks.

  5. Faster and Better LLMs via Latency-Aware Test-Time Scaling

    cs.CL 2025-05 conditional novelty 5.0 of 10

    Test-time scaling should be tuned for wall-clock latency rather than token count; branches plus speculative decoding win under time budgets.

  6. First Finish Search: Efficient Test-Time Scaling in Large Language Models

    cs.CL 2025-05 conditional novelty 4.0 of 10

    First Finish Search launches n parallel reasoning traces and returns the shortest one, improving accuracy on AIME benchmarks while cutting token use.

Pith tools