arXiv subjects

Aleksey Komissarov

Publications and source records attributed to Aleksey Komissarov.

8 recordsLinked to original sources

arXiv2026

AI-Research Agents in the Wild. From GitHub and arXiv to Regularities and Gaps

AI-research agents, or autoresearch systems, combine language models with tools, search, evaluation, and iterative modification of research artifacts. Their public software ecology is hard to compare because repositories, papers, benchmarks, libraries, and companion artifacts are often counted as one population. We connect two agent-drafted, human-adjudicated registries frozen on 10 June 2026: 139 canonical public repositories and 101 papers on AI-assisted research systems, each record carrying an evidence card anchored to its primary sources. Nine promoted design lineages contain 59 memberships among 52 repositories, seven of them assigned to two lineages. Against this evidence we examine six time-stamped candidate design regularities. A prospective audit of 25 newly ingested repositories observed zero of six specified trigger events, supplying bounded support for R1-R4; broader corpus evidence narrowed the original scope of R5, and a failed directional prediction leaves R6 exploratory. The paper-repository graph contains 212 curator-assigned relatedness edges: 64 of 101 papers carry at least one edge, the edges reach 23 of 139 repositories, and the six most-linked repositories carry 120 of the 212 edges (56.6%). A full-text check of seven papers shows the relation measures our curation, not the papers' citation behavior. An identity audit adjudicated against commit histories and public contributor records confirms at least 18 paper authors who also author a canonical registry repository (20 of 63 candidate author slots in 13 of 101 papers); a byline-matched tier reaches 58 identities but is reported separately and more weakly. The study contributes a source-grounded theory under prospective test, a curator-assigned map of paper-repository relatedness, and explicit limits on claims about public visibility and community structure.

cs.DL↗

arXiv2026

Anatomy of a Sound Neural Reasoner: One-Shot Amortization, First-Pass Poisoning, and Search Inertness in Clue-Rich Completion

Neural solvers are built to deduce, branch, and revise intermediate states. The Lattice Deduction Transformer (LDT) appears to do exactly that. In clue-rich Sudoku, it does not: one forward pass commits essentially the entire grid (every blank cell on standard 6x6, 94-96% on augmented 9x9), turning the iterative solver into a one-shot predictor wrapped in an exact verifier. All hard-slice failures are decided before search begins, when the first pass confidently deletes a value required by the true solution. We call this first-pass poisoning. Adding learned branching, MRV, backtracking, value exclusion, and shared nogoods (CoLT) does not change which Sudoku instances are solved; it cuts repeated invalid derivations 1,497-fold. At the frozen training budget, constraint-graph attention alone matches full-CoLT accuracy, while positional tables recover only under substantially longer training, indicating an optimization and sample-efficiency advantage rather than an absolute capacity difference. The diagnosis predicts two effective interventions. Digit-permutation augmentation raises 9x9 accuracy from below 1% to 96.5 +/- 0.3 across three training seeds on a symmetry-disjoint split. Test-time union over symmetry-transformed passes raises all three hard-slice checkpoints from 72.8-78.9% to 100% without retraining. On from-scratch graph coloring, one-shot behavior disappears and search changes accuracy. In clue-rich completion, LDT-like systems are one-shot amortized predictors rather than learned search procedures: accuracy is determined by calibration and symmetry, while search primarily removes computational waste.

cs.LG↗

arXiv2026

From Diagnosis to Inoculation: Building Cognitive Resistance to AI Disempowerment

Recent empirical research by Sharma et al. (2026) demonstrated that AI assistant interactions carry meaningful potential for situational human disempowerment, including reality distortion, value judgment distortion, and action distortion. While this work provides a critical diagnosis of the problem, concrete pedagogical interventions remain underexplored. I present an AI literacy framework built around eight cross-cutting Learning Outcomes (LOs), developed independently through teaching practice and subsequently found to align with Sharma et al.'s disempowerment taxonomy. I report a case study from a publicly available online course, where a co-teaching methodology--with AI serving as an active voice co-instructor--was used to deliver this framework. Drawing on inoculation theory (McGuire, 1961)--a well-established persuasion research framework recently applied to misinformation prebunking by the Cambridge school (van der Linden, 2022; Roozenbeek & van der Linden, 2019)--I argue that AI literacy cannot be acquired through declarative knowledge alone, but requires guided exposure to AI failure modes, including the sycophantic validation and authority projection patterns identified by Sharma et al. This application of inoculation theory to AI-specific distortion is, to my knowledge, novel. I discuss the convergence between the pedagogically-derived framework and Sharma et al.'s empirically-derived taxonomy, and argue that this convergence--two independent approaches arriving at similar problem descriptions--strengthens the case for both the diagnosis and the proposed educational response.

cs.HC↗

arXiv2026

Compressed code: the hidden effects of quantization and distillation on programming tokens

Large Language Models (LLMs) have demonstrated exceptional code generation capabilities, yet their token-level mechanisms remain underexplored, particularly in compressed models. Through systematic analysis of programming language token representations, we characterize how programming languages are encoded in LLM tokenizers by analyzing their vocabulary distribution and keyword coverage patterns. We introduce a novel cold-start probability analysis method that provides insights into model behavior without requiring explicit prompts. Additionally, we present a comprehensive evaluation of how different model optimization techniques - including quantization, distillation, model scaling, and task-specific fine-tuning - affect token-level representations and code generation quality. Our experiments, supported by comprehensive probability distribution analysis and evaluation metrics, reveal critical insights into token-level behavior and provide empirically-validated guidelines for maintaining code generation quality under various optimization constraints. These findings advance both theoretical understanding of LLM code generation and practical implementation of optimized models in production environments.

cs.SE↗

arXiv2026

Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets

We present a large-scale comparative study of 242 Latin and Cyrillic-script languages using subword-based methodologies. By constructing 'glottosets' from Wikipedia lexicons, we introduce a framework for simultaneous cross-linguistic comparison via Byte-Pair Encoding (BPE). Our approach utilizes rank-based subword vectors to analyze vocabulary overlap, lexical divergence, and language similarity at scale. Evaluations demonstrate that BPE segmentation aligns with morpheme boundaries 95% better than random baseline across 15 languages (F1 = 0.34 vs 0.15). BPE vocabulary similarity correlates significantly with genetic language relatedness (Mantel r = 0.329, p < 0.001), with Romance languages forming the tightest cluster (mean distance 0.51) and cross-family pairs showing clear separation (0.82). Analysis of 26,939 cross-linguistic homographs reveals that 48.7% receive different segmentations across related languages, with variation correlating to phylogenetic distance. Our results provide quantitative macro-linguistic insights into lexical patterns across typologically diverse languages within a unified analytical framework.

cs.CL↗

arXiv2026

SampoNLP: A Self-Referential Toolkit for Morphological Analysis of Subword Tokenizers

The quality of subword tokenization is critical for Large Language Models, yet evaluating tokenizers for morphologically rich Uralic languages is hampered by the lack of clean morpheme lexicons. We introduce SampoNLP, a corpus-free toolkit for morphological lexicon creation using MDL-inspired Self-Referential Atomicity Scoring, which filters composite forms through internal structural cues - suited for low-resource settings. Using the high-purity lexicons generated by SampoNLP for Finnish, Hungarian, and Estonian, we conduct a systematic evaluation of BPE tokenizers across a range of vocabulary sizes (8k-256k). We propose a unified metric, the Integrated Performance Score (IPS), to navigate the trade-off between morpheme coverage and over-splitting. By analyzing the IPS curves, we identify the "elbow points" of diminishing returns and provide the first empirically grounded recommendations for optimal vocabulary sizes (k) in these languages. Our study not only offers practical guidance but also quantitatively demonstrates the limitations of standard BPE for highly agglutinative languages. The SampoNLP library and all generated resources are made publicly available: https://github.com/AragonerUA/SampoNLP

cs.CL↗

arXiv2025

When repeats drive the vocabulary: a Byte-Pair Encoding analysis of T2T primate genomes

The emergence of telomere-to-telomere (T2T) genome assemblies has opened new avenues for comparative genomics, yet effective tokenization strategies for genomic sequences remain underexplored. In this pilot study, we apply Byte Pair Encoding (BPE) to nine T2T primate genomes including three human assemblies by training independent BPE tokenizers with a fixed vocabulary of 512,000 tokens using our custom tool, dnaBPE. Our analysis reveals that only 11,569 tokens are shared across all assemblies, while nearly 991,854 tokens are unique to a single genome, indicating a rapid decline in shared vocabulary with increasing assembly comparisons. Moreover, phylogenetic trees derived from token overlap failed to recapitulate established primate relationships, a discrepancy attributed to the disproportionate influence of species-specific high-copy repetitive elements. These findings underscore the dual nature of BPE tokenization: while it effectively compresses repetitive sequences, its sensitivity to high-copy elements limits its utility as a universal tool for comparative genomics. We discuss potential hybrid strategies and repeat-masking approaches to refine genomic tokenization, emphasizing the need for domain-specific adaptations in the development of large-scale genomic language models. The dnaBPE tool used in this study is open-source and available at https://github.com/aglabx/dnaBPE.

q-bio.GN↗

arXiv2024

Qtok: A Comprehensive Framework for Evaluating Multilingual Tokenizer Quality in Large Language Models

In the development of Large Language Models (LLMs), considerable attention has been given to the quality of training datasets. However, the role of tokenizers in the LLM training pipeline, particularly for multilingual models, has received less focus. The quality of tokenization can significantly impact a model's ability to handle diverse languages effectively. We introduce Qtok, a tool designed to assess tokenizer quality with a specific emphasis on their performance in multilingual contexts. Our research proposes a set of metrics for evaluating tokenizer quality, including measures of language coverage, token completeness, and distribution across languages and linguistic categories. Qtok applies these metrics to evaluate 13 distinct tokenizers from 58 publicly available models, analyzing their output across different linguistic contexts. Our analysis revealed significant variations in token distribution across languages and categories, highlighting potential biases and areas for improvement in current tokenization strategies. This research contributes to the field of tokenizer evaluation within multilingual LLM development by providing a systematic approach to assessing tokenizer quality. Our findings highlight the critical role of tokenization in multilingual LLM capability. The Qtok tool and our analysis methodology offer practical means for researchers to evaluate and improve tokenization strategies for multilingual applications. We offer a method to compare tokenizer quality across these metrics, which may be useful when selecting or adjusting tokenizers for specific multilingual LLM applications.

cs.CL↗