PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking
Fuente:
arXiv
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908978625118208 |
|---|---|
| author | Zhu, Wang Bill Yi, Qiutong Tony Jia, Robin Thomason, Jesse |
| author_facet | Zhu, Wang Bill Yi, Qiutong Tony Jia, Robin Thomason, Jesse |
| contents | Large language models (LLMs) perform substantially below human level on existing theory-of-mind (ToM) benchmarks, even when augmented with chain-of-thought prompting or probabilistic belief updates. We argue that these failures primarily arise from unreliable implicit state tracking rather than limitations in high-level reasoning. We introduce PDDL-Mind, a neuro-symbolic framework that decouples environment state evolution from belief inference. By translating narrative descriptions into explicit states and actions expressed in Planning Domain Definition Language (PDDL), and by verifying action-induced state transitions against a predefined domain, PDDL-Mind provides LLMs with a logically consistent and explicit representation of world states for ToM tasks. Experiments on MMToM-QA, MuMA and FanToM show that PDDL-Mind achieves over 5% absolute accuracy gain over the best existing state-of-the-art method on ToM benchmark questions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_17819 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking Zhu, Wang Bill Yi, Qiutong Tony Jia, Robin Thomason, Jesse Computation and Language Artificial Intelligence Large language models (LLMs) perform substantially below human level on existing theory-of-mind (ToM) benchmarks, even when augmented with chain-of-thought prompting or probabilistic belief updates. We argue that these failures primarily arise from unreliable implicit state tracking rather than limitations in high-level reasoning. We introduce PDDL-Mind, a neuro-symbolic framework that decouples environment state evolution from belief inference. By translating narrative descriptions into explicit states and actions expressed in Planning Domain Definition Language (PDDL), and by verifying action-induced state transitions against a predefined domain, PDDL-Mind provides LLMs with a logically consistent and explicit representation of world states for ToM tasks. Experiments on MMToM-QA, MuMA and FanToM show that PDDL-Mind achieves over 5% absolute accuracy gain over the best existing state-of-the-art method on ToM benchmark questions. |
| title | PDDL-Mind: Large Language Models are Capable on Belief Reasoning with Reliable State Tracking |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2604.17819 |