Course / Reading list Primary sources

Read the papers, not the summaries.

A verified, filterable list for Lecture 01 and the course. Every arXiv ID and DOI was checked when the lecture was written; venue claims should be re-checked before you quote them.

46 entries 5 threads Updated 2026-11-16 arXiv + DOI

The reading list

Scope · the Lecture 01 spine

This table is the verified spine of Lecture 01. Every live lecture ends with its own reading list, tied to that lecture's argument. The course-wide library will merge them here as the arc grows; until then, read this table as the foundation, not the whole bibliography.

Table 1 · Primary sources, grouped by thread.
PaperAuthors · yearThreadWhy read itLink
Neurosymbolic AI: the 3rd waveGarcez & Lamb · 2023SurveyThe framing paper; the “third wave” narrative.DOI
Neurosymbolic AI — Why, What, and How2023SurveyA compact map of the motivations and methods.arXiv:2305.00813
From Statistical Relational to Neuro-Symbolic AI2020SurveyThe bridge from probabilistic relational models to NeSy.arXiv:2003.08316
Neural-Symbolic Learning and Reasoning: A Survey2017SurveyThe older integration literature, still useful.arXiv:1711.03902
A Survey on Neural-symbolic Learning Systems2021SurveyA systematic taxonomy of learning systems.arXiv:2111.08164
Neurosymbolic Reinforcement Learning and Planning: A Survey2023SurveyThe RL/planning angle, closest to embodied applications.arXiv:2309.01038
Graph Neural Networks Meet Neural-Symbolic Computing2020SurveyThe graph-learning bridge; useful for your background.arXiv:2003.00330
Verification and Validation of Neurosymbolic AI2024SurveyWhat it means to test and assure a NeSy system.arXiv:2401.03188
Defining neurosymbolic AI2025SurveyA recent attempt to pin down the definition.arXiv:2507.11127
Challenges, Opportunities, and Misconceptions in Neurosymbolic AI2026SurveyThe current critical assessment; read after the basics.arXiv:2611.09356
DeepProbLog: Neural Probabilistic Logic ProgrammingManhaeve et al. · 2018InterfaceNeural predicates inside probabilistic logic; end-to-end training.arXiv:1805.10872
NeurASP: Embracing Neural Networks into Answer Set ProgrammingYang, Ishay & Lee · 2020InterfaceThe Sudoku example; ASP as the symbolic host.arXiv:2307.07700
Scallop: A Language for Neurosymbolic Programming2023InterfaceA programmable NeSy language with a differentiable engine.arXiv:2304.04812
ULLER: A Unified Language for Learning and Reasoning2024InterfaceA unified semantics for NeSy languages.arXiv:2405.00532
Logic Tensor Networks2022InterfaceFuzzy logic as a differentiable loss.arXiv:2012.13635
A Semantic Loss Function for Deep Learning with Symbolic Knowledge2018InterfaceThe canonical logic-as-loss paper.arXiv:1711.11157
A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference2022InterfaceScaling probabilistic NeSy inference.arXiv:2212.12393
On the Independence Assumption in Neurosymbolic Learning2024InterfaceWhy the common independence assumption is dangerous.arXiv:2404.08458
On the Hardness of Probabilistic Neurosymbolic Learning2024InterfaceThe computational limits of the probabilistic approach.arXiv:2406.04472
Learning Explanatory Rules from Noisy DataEvans & Grefenstette · 2018InterfaceDifferentiable ILP; learning logic programs from examples.arXiv:1711.04574
End-to-End Differentiable ProvingRocktäschel & Riedel · 2017InterfaceNeural theorem proving; the search interface.arXiv:1705.11040
DreamCoder: Growing generalizable, interpretable knowledgeEllis et al. · 2021InterfaceLibrary learning and program synthesis.arXiv:2006.08381
Solving olympiad geometry without human demonstrationsTrinh et al. · 2024InterfaceAlphaGeometry: a model proposes, a prover checks.DOI
LeanDojo: Theorem Proving with Retrieval-Augmented Language Models2023InterfaceThe Lean ecosystem for verified reasoning.arXiv:2306.15626
Neurosymbolic Conformal Classification2024InterfaceUncertainty guarantees for NeSy predictions.arXiv:2409.13585
T-ILR: a Neurosymbolic Integration for LTLf2025InterfaceTemporal logic as a NeSy constraint.arXiv:2508.15943
Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey2023InterfaceThe data interface: embeddings, constraints, rules.arXiv:2302.07200
LINC: A Neurosymbolic Approach for Logical Reasoning2023LanguageLLM + first-order logic prover; a clean tool-use baseline.arXiv:2310.15164
Logic-LM: Empowering LLMs with Symbolic SolversPan et al. · 2023LanguageTranslate, solve, self-refine; the canonical pipeline.arXiv:2305.12295
LLM+P: Empowering LLMs with Optimal Planning Proficiency2023LanguageNatural language to PDDL to a classical planner.arXiv:2304.11477
LLMs Can’t Plan, But Can Help Planning in LLM-Modulo FrameworksKambhampati et al. · 2024LanguageThe strongest statement of the verifier interface for LLMs.arXiv:2402.01817
Faith and Fate: Limits of Transformers on CompositionalityDziri et al. · 2023LanguageThe empirical case for the neural composition gap.arXiv:2305.18654
Intermediate Languages Matter2025LanguageThe formal language you choose changes NeSy LLM reasoning.arXiv:2509.04083
Neurosymbolic Language Reasoning as Satisfiability Modulo Theory2026LanguageSMT as the interface between language and logic.arXiv:2602.18095
Do As I Can, Not As I Say: Grounding Language in Robotic AffordancesAhn et al. · 2022EmbodimentSayCan: language grounded in what the robot can do.arXiv:2204.01691
Code as Policies: Language Model Programs for Embodied ControlLiang et al. · 2022EmbodimentPrograms as the interface between language and action.arXiv:2209.07753
AutoTAMP: Autoregressive Task and Motion Planning with LLMs2023EmbodimentLLMs as translators and checkers for TAMP.arXiv:2306.06531
ChatHTN: Interleaving Approximate (LLM) and Symbolic HTN Planning2025EmbodimentHTN planning as the symbolic backbone for an LLM.arXiv:2505.11814
The Neuro-Symbolic Concept LearnerMao et al. · 2019EmbodimentThe hook: perception, programs, and grounded composition.arXiv:1904.12584
ConceptGraphs: Open-Vocabulary 3D Scene Graphs2023EmbodimentScene graphs as the grounding layer for planning.arXiv:2309.16650
Learning for Long-Horizon Planning via Neuro-Symbolic Abductive Imitation2024EmbodimentAbduction as the interface between demonstration and plan.arXiv:2411.18201
Hierarchical Neuro-Symbolic Decision Transformer2025EmbodimentA recent attempt to put symbols inside a decision transformer.arXiv:2503.07148
CLEVR: A Diagnostic Dataset for Compositional Language and Visual ReasoningJohnson et al. · 2017BenchmarkThe diagnostic benchmark behind the hook; know its limits.arXiv:1612.06890
FOLIO: Natural Language Reasoning with First-Order Logic2022BenchmarkA benchmark for faithful logical reasoning in language.arXiv:2209.00840
LTLZinc: A Benchmarking Framework for Continual Learning and Neuro-Symbolic Temporal Reasoning2025BenchmarkA benchmark for temporal NeSy reasoning.arXiv:2507.17482
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision MakingLi et al. · 2024BenchmarkThe error taxonomy for embodied agents; use it to design evaluations.arXiv:2410.07166
Selection rule

This is a reading list, not a bibliography. It favors papers that made a conceptual contribution or defined a benchmark. Every entry has a stable arXiv ID or DOI; the “why read it” line is a position, not a summary of the abstract.

← Back to Lecture 01 · Concept map →