Paper
Bilevel Planning with Learned Symbolic Abstractions from Interaction Data
Authors
Fatih Dogangun, Burcu Kilic, Serdar Bahar, Emre Ugur
Abstract
Intelligent agents must reason over both continuous dynamics and discrete representations to generate effective plans in complex environments. Previous studies have shown that symbolic abstractions can emerge from neural effect predictors trained with a robot's unsupervised exploration. However, these methods rely on deterministic symbolic domains, lack mechanisms to verify the generated symbolic plans, and operate only at the abstract level, often failing to capture the continuous dynamics of the environment. To overcome these limitations, we propose a bilevel neuro-symbolic framework in which learned probabilistic symbolic rules generate candidate plans rapidly at the high level, and learned continuous effect models verify these plans and perform forward search when necessary at the low level. Our experiments on multi-object manipulation tasks demonstrate that the proposed bilevel method outperforms symbolic-only approaches, reliably identifying failing plans through verification, and achieves planning performance statistically comparable to continuous forward search while resolving most problems via efficient symbolic reasoning.
Metadata
Related papers
Cosmic Shear in Effective Field Theory at Two-Loop Order: Revisiting $S_8$ in Dark Energy Survey Data
Shi-Fan Chen, Joseph DeRose, Mikhail M. Ivanov, Oliver H. E. Philcox • 2026-03-30
Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation
Vitória Barin Pacela, Shruti Joshi, Isabela Camacho, Simon Lacoste-Julien, Da... • 2026-03-30
SNID-SAGE: A Modern Framework for Interactive Supernova Classification and Spectral Analysis
Fiorenzo Stoppa, Stephen J. Smartt • 2026-03-30
Acoustic-to-articulatory Inversion of the Complete Vocal Tract from RT-MRI with Various Audio Embeddings and Dataset Sizes
Sofiane Azzouz, Pierre-André Vuissoz, Yves Laprie • 2026-03-30
Rotating black hole shadows in metric-affine bumblebee gravity
Jose R. Nascimento, Ana R. M. Oliveira, Albert Yu. Petrov, Paulo J. Porfírio,... • 2026-03-30
Raw Data (Debug)
{
"raw_xml": "<entry>\n <id>http://arxiv.org/abs/2603.08599v1</id>\n <title>Bilevel Planning with Learned Symbolic Abstractions from Interaction Data</title>\n <updated>2026-03-09T16:47:03Z</updated>\n <link href='https://arxiv.org/abs/2603.08599v1' rel='alternate' type='text/html'/>\n <link href='https://arxiv.org/pdf/2603.08599v1' rel='related' title='pdf' type='application/pdf'/>\n <summary>Intelligent agents must reason over both continuous dynamics and discrete representations to generate effective plans in complex environments. Previous studies have shown that symbolic abstractions can emerge from neural effect predictors trained with a robot's unsupervised exploration. However, these methods rely on deterministic symbolic domains, lack mechanisms to verify the generated symbolic plans, and operate only at the abstract level, often failing to capture the continuous dynamics of the environment. To overcome these limitations, we propose a bilevel neuro-symbolic framework in which learned probabilistic symbolic rules generate candidate plans rapidly at the high level, and learned continuous effect models verify these plans and perform forward search when necessary at the low level. Our experiments on multi-object manipulation tasks demonstrate that the proposed bilevel method outperforms symbolic-only approaches, reliably identifying failing plans through verification, and achieves planning performance statistically comparable to continuous forward search while resolving most problems via efficient symbolic reasoning.</summary>\n <category scheme='http://arxiv.org/schemas/atom' term='cs.RO'/>\n <published>2026-03-09T16:47:03Z</published>\n <arxiv:primary_category term='cs.RO'/>\n <author>\n <name>Fatih Dogangun</name>\n </author>\n <author>\n <name>Burcu Kilic</name>\n </author>\n <author>\n <name>Serdar Bahar</name>\n </author>\n <author>\n <name>Emre Ugur</name>\n </author>\n </entry>"
}