mlsanityData to 7 Oct 2026

Teaching LLMs to Ask: Self-Querying Category-Theoretic Planning for Under-Specified Reasoning

arXiv 2601.20014 ↗First posted 27 Jan 2026cs.AIcited by 2

On the map: LLM reasoning → Test-time compute and efficient thinking

Abstract (arXiv)

Inference-time planning with large language models frequently breaks under partial observability: when task-critical preconditions are not specified at query time, models tend to hallucinate missing facts or produce plans that violate hard constraints. We introduce Self-Querying Bidirectional Categorical Planning (SQ-BCP), which explicitly represents precondition status (textttSat/textttViol/textttUnk) and resolves unknowns via (i) targeted self-queries to an oracle/user or (ii) bridging hypotheses that establish the missing condition through an additional action. SQ-BCP performs bidirectional search and invokes a pullback-based verifier as a categorical certificate of goal compatibility, while using distance-based scores only for ranking and pruning. We prove that when the verifier succeeds and hard constraints pass deterministic checks, accepted plans are compatible with goal requirements; under bounded branching and finite resolution depth, SQ-BCP finds an accepting plan when one exists. Across WikiHow and RecipeNLG tasks with withheld preconditions, SQ-BCP reduces resource-violation rates to 14.9% and 5.8% (vs. 26.0% and 15.7% for the best baseline), while maintaining competitive reference quality.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Test-time compute and efficient thinking, one of 17 directions in LLM reasoning. Builds on 12 of its 53 references that are in the map. First posted on arXiv 27 Jan 2026.

Builds on

12 of 53 references.

References · 12

  1. 2022Self-Consistency Improves Chain of Thought Reasoning in Language Modelscited by 5,601
  2. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  3. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  4. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  5. 2022PAL: Program-aided Language Modelscited by 635
  6. 2022Large Language Models are Better Reasoners with Self-Verificationcited by 304
  7. 2022Active Example Selection for In-Context Learningcited by 195
  8. 2018Learning to Ask Good Questions: Ranking Clarification Questions using Neural Expected Value of Perfect Informationcited by 110
  9. 2025PlanGenLLMs: A Modern Survey of LLM Planning Capabilitiescited by 82
  10. 2024Aligning Language Models to Explicitly Handle Ambiguitycited by 55
  11. 2025Enforcing Temporal Constraints for LLM Agentscited by 31
  12. 2020Online Scheduling with Makespan Minimization: State of the Art Results, Research Challenges and Open Problemscited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Adaptive Test-Time Compute Allocation via Learned Heuristics over Categorical Structurecited by 5
  2. 2026Active Epistemic Control for Query-Efficient Verified Planningcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2024Thinking Forward and Backward: Effective Backward Planning with Large Language Models
  2. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Tasks
  3. 2025Policy Guided Tree Search for Enhanced LLM Reasoning
  4. 2026Analysis of Optimality of Large Language Models on Planning Problems
  5. 2025Explore-Execute Chain: Towards an Efficient Structured Reasoning Paradigm
  6. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks
  7. 2025Self-Reflective Planning with Knowledge Graphs: Enhancing LLM Reasoning Reliability for Question Answering
  8. 2025Think Smarter not Harder: Adaptive Reasoning with Inference Aware Optimization