mlsanityData to 14 Oct 2026

Zero-Shot Goal Recognition with Large Language Models

arXiv 2605.15333 ↗First posted 14 May 2026cs.AIcited by 0

On the map: LLM reasoning → Reasoning for agents, planning and code

Abstract (arXiv)

Large language models have recently reached near-parity with classical planners on well-known planning domains, yet this competence relies on world-knowledge exploitation rather than genuine symbolic reasoning. Goal recognition is a complementary abductive task structurally better suited to LLM strengths: it consists of evaluating consistency with world knowledge rather than generating novel action sequences. This paper provides the first systematic zero-shot evaluation of frontier LLMs as goal recognisers on key classical PDDL benchmarks. Our results show that LLM competence on goal recognition is uneven: some models scale with evidence and approach landmark-based accuracy at full observations, while others remain anchored to world-knowledge priors regardless of how much evidence accumulates. Qualitative analysis of model reasoning traces reveals that this divergence reflects a fundamental difference in evidence integration rather than domain familiarity. These findings position goal recognition as a principled benchmark for the foundational planning knowledge of LLMs.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning. Builds on 11 of its 27 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

11 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024LLMs Can't Plan, But Can Help Planning in LLM-Modulo Frameworks2 Feb
  2. 2023On the Planning Abilities of Large Language Models : A Critical Investigation25 May
  3. 2022PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change21 Jun

Other references · 8

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2023Lost in the Middle: How Language Models Use Long Contextscited by 3,455
  3. 2024On the Self-Verification Limitations of Large Language Models on Reasoning and Planning Taskscited by 142
  4. 2019Landmark-Based Approaches for Goal Recognition as Planningcited by 21
  5. 2022Goal Recognition as a Deep Learning Task: the GRNet Approachcited by 9
  6. 2025Frontier Large Language Models Rival State-of-the-Art Plannerscited by 7
  7. 2023Real-time goal recognition using approximations in Euclidean spacecited by 3
  8. 2023Temporally Extended Goal Recognition in Fully Observable Non-Deterministic Domain Modelscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2023Translating Natural Language to Planning Goals with Large-Language Models
  2. 2026Latent Goal Prediction from Language for Model-Based Planning
  3. 2024Chasing Progress, Not Perfection: Revisiting Strategies for End-to-End LLM Plan Generation
  4. 2025Can LLM-Reasoning Models Replace Classical Planning? A Benchmark Study
  5. 2024Evaluating Vision-Language Models as Evaluators in Path Planning
  6. 2023Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning
  7. 2026A Close Look At World Model Recovery In Supervised Fine-Tuned LLM Planners
  8. 2025On the Limits of Innate Planning in Large Language Models