mlsanityData to 14 Oct 2026

Quantum-Inspired Trace-Augmented Evidence Selection for Reasoning over Structured Hypothesis Spaces

arXiv 2606.06941 ↗First posted 5 Jun 2026cs.AIcited by 0

On the map: LLM reasoning → Prompting and chain-of-thought reasoning

Abstract (arXiv)

Large language models (LLMs) now solve a wide range of expert-level exams at or above human level, yet remain brittle on specialised, evidence-intensive domains such as law. On these tasks, errors arise not only from gaps in world knowledge but also from subtle distinctions between pieces of evidence and inconsistent use of supporting evidence. The most common aggregator over sampled chain-of-thought (CoT) traces, majority vote, returns the most popular answer regardless of whether its evidence is actually strongest. We propose to treat the selection of CoT reasoning fragments into a set of evidence as an explicit combinatorial optimisation problem, allowing well-supported but minority hypotheses to override noisy majorities, and to evaluate the approach on legal-reasoning benchmarks that are particularly sensitive to evidence quality. We introduce EP-HUBO (Evidence Pool Higher-Order Binary Optimisation), which generates multiple CoT traces with a small local model, parses fragments into per-hypothesis evidence pools, solves a higher-order unconstrained binary optimisation per pool with quality-derived weights (relevance, specificity, distinctiveness), and delegates a single adjudication call per question to a frontier model. We evaluate EP-HUBO on two evidence-intensive legal benchmarks using both simulated annealing on classical hardware and the Dirac-3 photonic entropy-quantum machine from Quantum Computing Inc. HUBO-style optimisation gives a principled way to aggregate reasoning fragments while preserving minority-but-correct hypotheses, and is most valuable in low-contamination domains where frontier models have not already absorbed the benchmark material.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Prompting and chain-of-thought reasoning, one of 17 directions in LLM reasoning. Builds on 26 of its 36 references that are in the map. First posted on arXiv 5 Jun 2026.

Builds on

26 of 36 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Combinatorial Reasoning: Selecting Reasons in Generative AI Pipelines via Combinatorial Optimization19 Jun
  2. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Models21 Mar
  3. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Models28 Jan

Other references · 23

  1. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  2. 2024MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmarkcited by 1,848
  3. 2022Quantifying Memorization Across Neural Language Modelscited by 763
  4. 2024Mixture-of-Agents Enhances Large Language Model Capabilitiescited by 438
  5. 2022Self-critiquing models for assisting human evaluatorscited by 380
  6. 2023NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmarkcited by 348
  7. 2022Generating Sequences by Learning to Self-Correctcited by 277
  8. 2022Data Contamination: From Memorization to Exploitationcited by 236
  9. 2025Scalable Best-of-N Selection for Large Language Models via Self-Certaintycited by 187
  10. 2022Synchromesh: Reliable code generation from pre-trained language modelscited by 156
  11. 2025Towards Thinking-Optimal Scaling of Test-Time Compute for LLM Reasoningcited by 119
  12. 2023Efficient Benchmarking of Language Modelscited by 71
11 more
  1. 2018SparseMAP: Differentiable Sparse Structured Inferencecited by 62
  2. 2025Rethinking Mixture-of-Agents: Is Mixing Different Large Language Models Beneficial?cited by 54
  3. 2025LEXam: Benchmarking Legal Reasoning on 340 Law Examscited by 54
  4. 2025Towards Reasoning Ability of Small Language Modelscited by 29
  5. 2025Ensemble Learning for Large Language Models in Text and Code Generation: A Surveycited by 9
  6. 2025Optimal Self-Consistency for Efficient Reasoning with Large Language Modelscited by 9
  7. 2025Quantum Natural Language Processing: A Comprehensive Review of Models, Methods, and Applicationscited by 4
  8. 2025Bench360: Benchmarking Local LLM Inference from 360 Degreescited by 4
  9. 2025LLM-QUBO: An End-to-End Framework for Automated QUBO Transformation from Natural Language Problem Descriptionscited by 3
  10. 2014On Quadratization of Pseudo-Boolean Functionscited by 2
  11. 2025Quantum Annealing for Machine Learning: Applications in Feature Selection, Instance Selection, and Clusteringcited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Can AI Validate Science? Benchmarking LLMs for Accurate Scientific Claim rightarrow Evidence Reasoning
  2. 2026ART: Adaptive Reasoning Trees for Explainable Claim Verification
  3. 2025Evaluating Test-Time Scaling LLMs for Legal Reasoning: OpenAI o1, DeepSeek-R1, and Beyond
  4. 2026Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
  5. 2025CoT-X: An Adaptive Framework for Cross-Model Chain-of-Thought Transfer and Optimization
  6. 2025Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
  7. 2022Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
  8. 2026TRACES: Tagging Reasoning Steps for Adaptive Cost-Efficient Early-Stopping