Pith. sign in

REVIEW 13 cited by

Evolving Deeper LLM Thinking

Not yet reviewed by Pith; the record is open.

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

Evolving Deeper LLM Thinking

classification cs.AI
keywords inferenceevolutionlanguagemindapproachnaturalproblemproposed
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
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 with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 13 Pith papers

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

  1. Joint Consistency: A Unified Test-Time Aggregation Framework via Energy Minimization

    cs.AI 2026-05 unverdicted novelty 7.0

    Joint Consistency casts test-time aggregation as Ising-type energy minimization with pairwise LLM-judge interactions, subsuming voting methods and outperforming baselines across reasoning tasks.

  2. Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

    cs.CL 2026-04 unverdicted novelty 7.0

    CoT-PoT ensembling achieves self-consistency accuracy in LLMs with only two samples for 78.6% of tasks, reducing computation by 9.3x compared to standard methods.

  3. Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning

    cs.CL 2026-04 accept novelty 7.0

    Cross-modal agreement between chain-of-thought and program-of-thought reasoning enables self-consistency with only two LLM samples, reducing sampling cost by 9.3x while improving accuracy.

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

    cs.CL 2025-11 unverdicted novelty 7.0

    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.

  5. REVES: REvision and VErification--Augmented Training for Test-Time Scaling

    cs.LG 2026-06 unverdicted novelty 6.0

    REVES augments LLM post-training by decoupling revision and verification signals from successful multi-step trajectories, reporting +6.5 point gains on LiveCodeBench over RL baselines.

  6. SeLaR: Selective Latent Reasoning in Large Language Models

    cs.CL 2026-04 unverdicted novelty 6.0

    SeLaR selectively applies latent soft reasoning in LLMs via entropy gating and contrastive regularization, outperforming standard CoT on five benchmarks without training.

  7. Procedural Knowledge at Scale Improves Reasoning

    cs.CL 2026-04 conditional novelty 6.0

    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.

  8. Procedural Knowledge at Scale Improves Reasoning

    cs.CL 2026-04 unverdicted novelty 6.0

    Reasoning Memory decomposes reasoning trajectories into 32 million subquestion-subroutine pairs and retrieves them via in-thought prompts to improve language model performance on math, science, and coding benchmarks b...

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

    cs.CL 2025-11 reject novelty 6.0

    An LLM-driven evolutionary framework that writes and evolves Python-coded trading factors reports large gains in predictive accuracy on CSI300, but with incomplete validation.

  10. AlphaMemo: Structured Search-Process Memory for Self-Evolving Alpha Mining Agents

    cs.AI 2026-05 unverdicted novelty 5.0

    AlphaMemo equips LLM alpha-mining agents with AST-diff motif memory, residual learning, and asymmetric veto control to improve out-of-sample factor discovery on CSI 500 and S&P 500.

  11. ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling

    cs.AI 2026-05 unverdicted novelty 5.0

    ExComm adds cross-agent conflict detection and soft belief correction plus trajectory diversification to agentic test-time scaling, yielding 5-6% gains over baselines on AIME and GAIA benchmarks.

  12. GEAR: Genetic AutoResearch for Agentic Code Evolution

    cs.NE 2026-05 unverdicted novelty 5.0

    GEAR applies genetic algorithms to maintain and evolve multiple research states in autonomous code agents, outperforming single-path baselines by continuing to discover improvements over extended runs.

  13. The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes

    cs.CL 2026-06 unverdicted novelty 4.0

    A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.