Cover Image

Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Tomlinson, Kiran, Schnabel, Tobias, Swaminathan, Adith, Neville, Jennifer
Format:	Preprint
Published:	2026
Subjects:	Artificial Intelligence Formal Languages and Automata Theory Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Lost in Transmission: When and Why LLMs Fail to Reason Globally
by: Schnabel, Tobias, et al.
Published: (2025)

Probabilistic Regular Tree Priors for Scientific Symbolic Reasoning
by: Schneider, Tim, et al.
Published: (2023)

Hilbert: Recursively Building Formal Proofs with Informal Reasoning
by: Varambally, Sumanth, et al.
Published: (2025)

HERMES: Towards Efficient and Verifiable Mathematical Reasoning in LLMs
by: Ospanov, Azim, et al.
Published: (2025)

InductionBench: LLMs Fail in the Simplest Complexity Class
by: Hua, Wenyue, et al.
Published: (2025)

The Sparse Tsetlin Machine: Sparse Representation with Active Literals
by: Østby, Sebastian, et al.
Published: (2024)

Mechanics of Learned Reasoning 1: TempoBench, A Benchmark for Interpretable Deconstruction of Reasoning System Performance
by: Holzer, Nikolaus, et al.
Published: (2025)

CoT-TL: Low-Resource Temporal Knowledge Representation of Planning Instructions Using Chain-of-Thought Reasoning
by: Manas, Kumar, et al.
Published: (2024)

Language Generation: Complexity Barriers and Implications for Learning
by: Arenas, Marcelo, et al.
Published: (2025)

On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
by: Nowak, Franz, et al.
Published: (2024)

RegexPSPACE: A Benchmark for Evaluating LLM Reasoning on PSPACE-complete Regex Problems
by: Jin, Hyundong, et al.
Published: (2025)

MinMax Recurrent Neural Cascades
by: Ronca, Alessandro
Published: (2026)

Robust Probabilistic Model Checking with Continuous Reward Domains
by: Ji, Xiaotong, et al.
Published: (2025)

Scalable Anytime Algorithms for Learning Fragments of Linear Temporal Logic
by: Raha, Ritam, et al.
Published: (2021)

Expressive Reward Synthesis with the Runtime Monitoring Language
by: Donnelly, Daniel, et al.
Published: (2025)

Neural Networks as Universal Finite-State Machines: A Constructive Deterministic Finite Automaton Theory
by: Dhayalkar, Sahil Rajesh
Published: (2025)

Tractable Offline Learning of Regular Decision Processes
by: Deb, Ahana, et al.
Published: (2024)

Analyzing constrained LLM through PDFA-learning
by: Carrasco, Matías, et al.
Published: (2024)

Learning Formal Specifications from Membership and Preference Queries
by: Shah, Ameesh, et al.
Published: (2023)

Extracting Robust Register Automata from Neural Networks over Data Sequences
by: Hong, Chih-Duo, et al.
Published: (2025)

The 4/$δ$ Bound: Designing Predictable LLM-Verifier Systems for Formal Method Guarantee
by: Dantas, PIerre, et al.
Published: (2025)

LLMs as Probabilistic Minimally Adequate Teachers for DFA Learning
by: Chen, Lekai, et al.
Published: (2024)

TheoremLlama: Transforming General-Purpose LLMs into Lean4 Experts
by: Wang, Ruida, et al.
Published: (2024)

Beyond Memorization: Testing LLM Reasoning on Unseen Theory of Computation Tasks
by: Shelat, Shlok, et al.
Published: (2026)

TeLoGraF: Temporal Logic Planning via Graph-encoded Flow Matching
by: Meng, Yue, et al.
Published: (2025)

Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
by: Yalcinkaya, Beyazit, et al.
Published: (2024)

The Lottery LLM Hypothesis, Rethinking What Abilities Should LLM Compression Preserve?
by: Tang, Zhenheng, et al.
Published: (2025)

Exploring Major Transitions in the Evolution of Biological Cognition With Artificial Neural Networks
by: Voudouris, Konstantinos, et al.
Published: (2025)

Automata Extraction from Transformers
by: Zhang, Yihao, et al.
Published: (2024)

Provably Correct Automata Embeddings for Optimal Automata-Conditioned Reinforcement Learning
by: Yalcinkaya, Beyazit, et al.
Published: (2025)

$L^*LM$: Learning Automata from Examples using Natural Language Oracles
by: Vazquez-Chanlatte, Marcell, et al.
Published: (2024)

Formal-LLM: Integrating Formal Language and Natural Language for Controllable LLM-based Agents
by: Li, Zelong, et al.
Published: (2024)

FormalAlign: Automated Alignment Evaluation for Autoformalization
by: Lu, Jianqiao, et al.
Published: (2024)

Finite Sentence-Interface Control for Learning Bounded-Fan-Out Linear MCFGs under Fixed Monoid Typing
by: Kuriyama, Takayuki
Published: (2026)

Reasoning about Rare-Event Reachability in Stochastic Vector Addition Systems via Affine Vector Spaces
by: Jeppson, Joshua, et al.
Published: (2025)

Constructing a BPE Tokenization DFA
by: Berglund, Martin, et al.
Published: (2024)

Neuro-Symbolic Compliance: Integrating LLMs and SMT Solvers for Automated Financial Legal Analysis
by: Hsia, Yung-Shen, et al.
Published: (2026)

Infinite Time Turing Machines and their Applications
by: Weerawarana, Rukmal, et al.
Published: (2025)

Automata Learning of Preferences over Temporal Logic Formulas from Pairwise Comparisons
by: Rahmani, Hazhar, et al.
Published: (2025)

A New Era in Software Security: Towards Self-Healing Software via Large Language Models and Formal Verification
by: Tihanyi, Norbert, et al.
Published: (2023)