Tootfinder

This is everything I could never get out of #sonicpi:

Replaced article(s) found for cs.CV. https://arxiv.org/list/cs.CV/new
[5/5]:
Imagine, Verify, Execute: Memory-Guided Agentic Exploration with Vision-Language Models

Bhatt Conjectures: On Necessary-But-Not-Sufficient Benchmark Tautology for Human Like Reasoning
Manish Bhatt
https://arxiv.org/abs/2506.11423 https://

Bhatt Conjectures: On Necessary-But-Not-Sufficient Benchmark Tautology for Human Like Reasoning
Debates about whether Large Language or Reasoning Models (LLMs/LRMs) truly reason or merely pattern-match suffer from shifting goal posts. In my personal opinion, two analytic--hence "tautological"--benchmarks cut through that fog in my mental model. In this paper, I attempt to write down my mental model in concrete terms.

With the advent of ELIZA, Joseph Weizenbaum's first psychotherapist chatbot, NLP took another major step with pattern-based substitution algorithms based on simple regular expressions.
Weizenbaum, Joseph (1966). ELIZA—a computer program for the study of natural language communication between man and machine. Com. of the ACM. 9: 36–45.

Superstudent intelligence in thermodynamics
Rebecca Loubet, Pascal Zittlau, Marco Hoffmann, Luisa Vollmer, Sophie Fellenz, Heike Leitte, Fabian Jirasek, Johannes Lenhard, Hans Hasse
https://arxiv.org/abs/2506.09822

Superstudent intelligence in thermodynamics
In this short note, we report and analyze a striking event: OpenAI's large language model o3 has outwitted all students in a university exam on thermodynamics. The thermodynamics exam is a difficult hurdle for most students, where they must show that they have mastered the fundamentals of this important topic. Consequently, the failure rates are very high, A-grades are rare - and they are considered proof of the students' exceptional intellectual abilities. This is because pattern learning does…

Multi-Language Detection of Design Pattern Instances
Hugo Andrade, Jo\~ao Bispo, Filipe F. Correia
https://arxiv.org/abs/2506.03903 https://

Multi-Language Detection of Design Pattern Instances
Code comprehension is often supported by source code analysis tools which provide more abstract views over software systems, such as those detecting design patterns. These tools encompass analysis of source code and ensuing extraction of relevant information. However, the analysis of the source code is often specific to the target programming language. We propose DP-LARA, a multi-language pattern detection tool that uses the multi-language capability of the LARA framework to support finding p…

Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Jiandong Shao, Yao Lu, Jianfei Yang
https://arxiv.org/abs/2506.01734 https://

Benford's Curse: Tracing Digit Bias to Numerical Hallucination in LLMs
Large Language Models (LLMs) exhibit impressive performance on complex reasoning tasks, yet they frequently fail on basic numerical problems, producing incorrect outputs. Inspired by Benford's Law -- a statistical pattern where lower digits occur more frequently as leading digits -- we hypothesize that the long-tailed digit distributions in web-collected corpora may be learned by LLMs during pretraining, leading to biased numerical generation. To investigate the hypothesis, we first examine whe…

Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
Anjana Sarkar, Soumyendu Sarkar
https://arxiv.org/abs/2506.05364 https…

Survey of LLM Agent Communication with MCP: A Software Design Pattern Centric Review
This survey investigates how classical software design patterns can enhance the reliability and scalability of communication in Large Language Model (LLM)-driven agentic AI systems, focusing particularly on the Model Context Protocol (MCP). It examines the foundational architectures of LLM-based agents and their evolution from isolated operation to sophisticated, multi-agent collaboration, addressing key communication hurdles that arise in this transition. The study revisits well-established pa…

This https://arxiv.org/abs/2505.19988 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csDB_…

Automatic Metadata Extraction for Text-to-SQL
Large Language Models (LLMs) have recently become sophisticated enough to automate many tasks ranging from pattern finding to writing assistance to code generation. In this paper, we examine text-to-SQL generation. We have observed from decades of experience that the most difficult part of query development lies in understanding the database contents. These experiences inform the direction of our research. Text-to-SQL benchmarks such as SPIDER and Bird contain extensive metadata that is gener…

This https://arxiv.org/abs/2506.03903 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csSE_…

Multi-Language Detection of Design Pattern Instances
Code comprehension is often supported by source code analysis tools which provide more abstract views over software systems, such as those detecting design patterns. These tools encompass analysis of source code and ensuing extraction of relevant information. However, the analysis of the source code is often specific to the target programming language. We propose DP-LARA, a multi-language pattern detection tool that uses the multi-language capability of the LARA framework to support finding p…

This https://arxiv.org/abs/2405.07671 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csFL_…

Constructing a BPE Tokenization DFA
Many natural language processing systems operate over tokenizations of text to address the open-vocabulary problem. In this paper, we give and analyze an algorithm for the efficient construction of deterministic finite automata (DFA) designed to operate directly on tokenizations produced by the popular byte pair encoding (BPE) technique. This makes it possible to apply many existing techniques and algorithms to the tokenized case, such as pattern matching, equivalence checking of tokenization d…