mlsanityData to 14 Oct 2026

Preference Reasoning under Indeterminacy in Large Language Models

arXiv 2608.18631 ↗First posted 19 Aug 2026cs.AI cs.GT cs.LGcited by 0

On the map: LLM reasoning → Reasoning benchmarks and evaluation

also in 1 more
Abstract (arXiv)

As large language models evolve into decision-making agents, the ability to reason over preferences becomes fundamental to alignment, coordination, and collective intelligence. Yet, unlike standard benchmarks, real-world preference reasoning is inherently indeterminate: information may be incomplete, and valid solutions may not exist. We argue that indeterminacy, rather than correctness alone, is a central challenge for AI reasoning. We formalize this challenge along two axes, (i) epistemic indeterminacy, arising from incomplete, partial, or expressive preferences, and (ii) structural indeterminacy, arising from the non-existence of solutions under standard social choice concepts. Across a hierarchy of tasks, we show that state-of-the-art language models systematically fail to distinguish between determined and undetermined instances, exhibiting miscalibrated reasoning even in verification settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning. Builds on 26 of its 83 references that are in the map. First posted on arXiv 19 Aug 2026.

Builds on

26 of 83 references.

Closest ancestors · 1

Same direction, newest first

  1. 2026Beyond Confidence: Rethinking Self-Assessments for Performance Prediction in LLMs8 May

Other references · 25

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,879
  3. 2024LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Codecited by 2,004
  4. 2022Language Models (Mostly) Know What They Knowcited by 1,856
  5. 2025gpt-oss-120b & gpt-oss-20b Model Cardcited by 1,386
  6. 2025OpenAI GPT-5 System Cardcited by 989
  7. 2023Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formattingcited by 817
  8. 2025Humanity's Last Examcited by 491
  9. 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexitycited by 302
  10. 2024Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedbackcited by 100
  11. 2024Game-theoretic LLM: Agent Workflow for Negotiation Gamescited by 56
  12. 2024Bayesian Preference Elicitation with Language Modelscited by 34
13 more
  1. 2025LLM Strategic Reasoning: Agentic Study through Behavioral Game Theorycited by 17
  2. 2025Understanding LLM Agent Behaviours via Game Theory: Strategy Recognition, Biases and Multi-Agent Dynamicscited by 11
  3. 2016Top-K Ranking from Pairwise Comparisons: When Spectral Ranking is Optimalcited by 10
  4. 2025EconEvals: Benchmarks and Litmus Tests for Economic Decision-Making by LLM Agentscited by 10
  5. 2026Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Unitscited by 10
  6. 2026When Agents Say One Thing and Do Another: Validating Elicited Beliefs from LLMscited by 10
  7. 2025Accelerated Preference Elicitation with LLM-Based Proxiescited by 9
  8. 2025Asking Clarifying Questions for Preference Elicitation With Large Language Modelscited by 7
  9. 2025The Illusion of Rationality: Tacit Bias and Strategic Dominance in Frontier LLM Negotiation Gamescited by 3
  10. 2026Discovering Differences in Strategic Behavior Between Humans and LLMscited by 3
  11. 2025Social Welfare Function Leaderboard: When LLM Agents Allocate Social Welfarecited by 2
  12. 2021Balanced House Allocationcited by 1
  13. 2026Large Language Models for Designing Participatory Budgeting Rulescited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Ask, Relax, or Act? Evaluating Actionable Indeterminacy in LLM Preference Reasoning
  2. 2024Aligning with Logic: Measuring, Evaluating and Improving Logical Preference Consistency in Large Language Models
  3. 2025Beyond Mimicry: Preference Coherence in LLMs
  4. 2025Extended Inductive Reasoning for Personalized Preference Inference from Behavioral Signals
  5. 2025The Seeds of Scheming: Weakness of Will in the Building Blocks of Agentic Systems
  6. 2024A dataset of questions on decision-theoretic reasoning in Newcomb-like problems
  7. 2024Beyond Preferences in AI Alignment
  8. 2026Reasoning aligns language models to human cognition