arXiv subjects

Stefan Krsteski

Publications and source records attributed to Stefan Krsteski.

7 recordsLinked to original sources

arXiv2026

Predicting Task Difficulty Without Rollouts

A fundamental challenge in evaluating and training autonomous agents is measuring the intrinsic difficulty of the tasks they attempt. Estimating this quantity can be useful for environment designers creating synthetic data or benchmarks, as well as for constructing training curricula, thereby offering a way to reduce compute costs. Such an estimation becomes increasingly important as agents (particularly LLM-based) move into longer-horizon domains, where empirical trial-and-error becomes a severe computational bottleneck. However existing work is largely confined to static tasks and relies on evaluation metrics that, as we show, can give an incomplete picture of predictive performance. In this paper we study ex ante difficulty prediction across 17 agentic benchmarks spanning coding, mathematics, machine learning, web navigation, function calling, and other domains. We find that AUC can mask poor difficulty estimates, identify token-level entropy as a useful predictive signal, and demonstrate how residuals between expected and observed difficulty can expose environment flaws such as contamination and infeasibility.

cs.LG↗

arXiv2026

Messier: A High-Resolution Corpus for Cross-Benchmark Agent Evaluation

Comprehensively evaluating AI agents across interactive environments is difficult due to fragmented tasks, scaffolds, verifiers, and scoring rules. Unfortunately, existing efforts to unify these evaluations are limited in scale and domain, making costly reruns necessary and leaving available data incomparable. We introduce MESSIER, a unified corpus of 957,611 records spanning 30 benchmarks, 745 agents, 11,891 tasks, and 74,263 verifiers. MESSIER combines public evaluation results with new runs on six underrepresented professional and scientific benchmarks, standardizing their heterogeneous components into a common schema. Using this corpus, we show that frontier progress is uneven across benchmark groups, with function-calling evaluations largely saturated, programming improving fastest, and enterprise workflows remaining most challenging. Counterfactual rescoring further shows that strict all-pass scoring in multi-verifier tasks can alter agent rankings. Finally, we derive capability scores from our corpus that correlate with Epoch's Evaluation Capability Index rankings at Spearman \r{ho} = 0.84. The scores can also be estimated for subsets defined by domain, occupation, action space, or verifier type. In essence, MESSIER is a reusable resource for studying agent performance at scale, and a basis for designing better evaluations.

cs.AI↗

arXiv2026

Synthetic Persona Pretraining: Alignment from Token Zero

As language-model-based AI is increasingly deployed in autonomous settings, aligning its goals and values with those of humans becomes critical. Today, alignment, and the assistant identity itself, are typically introduced only after pretraining, once behavioral priors are already established. This can make values a thin overlay, rather than deeply rooted, and facilitate subsequent misalignment. Pursuing a different paradigm, we introduce Synthetic Persona Pretraining (SPP), which installs the desired assistant persona from token zero in pretraining. First, we annotate pretraining documents with value-aligned first-person reflections derived from a normative value constitution. Second, we pretrain via the standard cross-entropy loss on standard pretraining documents as well as their reflections, which installs the desired persona among a multitude of other personas. Finally, we post-train on user-assistant dialogue data, which binds this desired persona to the assistant identity, a process we call persona binding. By pretraining models up to 3B parameters on 500B tokens, we show that SPP improves constitution following and jailbreak robustness, and reduces the misalignment rate in out-of-distribution moral dilemmas, while preserving capabilities. Early intervention matters: compared with alignment from token zero, introducing SPP only at the end of pretraining yields weaker constitution adherence, does not shift value priorities, and leads to less aligned choices in dilemmas. This advantage depends on persona binding and, importantly, increases with pretraining budget. Overall, our results show that shaping values early is critical for alignment and establish pretraining-time persona interventions as an effective approach to do so.

cs.LG↗

arXiv2025

Valid Survey Simulations with Limited Human Data: The Roles of Prompting, Fine-Tuning, and Rectification

Surveys provide valuable insights into public opinion and behavior, but their execution is costly and slow. Large language models (LLMs) have been proposed as a scalable, low-cost substitute for human respondents, but their outputs are often biased and yield invalid estimates. We study the interplay between synthesis methods that use LLMs to generate survey responses and rectification methods that debias population estimates, and explore how human responses are best allocated between them. Using two panel surveys with questions on nutrition, politics, and economics, we find that synthesis alone introduces substantial bias (24-86%), whereas combining it with rectification reduces bias below 5% and increases effective sample size by up to 14%. Overall, we challenge the common practice of using all human responses for fine-tuning, showing that under a fixed budget, allocating most to rectification results in far more effective estimation.

cs.CL↗

arXiv2025

MMORE: Massive Multimodal Open RAG & Extraction

We introduce MMORE, an open-source pipeline for Massive Multimodal Open RetrievalAugmented Generation and Extraction, designed to ingest, transform, and retrieve knowledge from heterogeneous document formats at scale. MMORE supports more than fifteen file types, including text, tables, images, emails, audio, and video, and processes them into a unified format to enable downstream applications for LLMs. The architecture offers modular, distributed processing, enabling scalable parallelization across CPUs and GPUs. On processing benchmarks, MMORE demonstrates a 3.8-fold speedup over single-node baselines and 40% higher accuracy than Docling on scanned PDFs. The pipeline integrates hybrid dense-sparse retrieval and supports both interactive APIs and batch RAG endpoints. Evaluated on PubMedQA, MMORE-augmented medical LLMs improve biomedical QA accuracy with increasing retrieval depth. MMORE provides a robust, extensible foundation for deploying task-agnostic RAG systems on diverse, real-world multimodal data. The codebase is available at https://github.com/swiss-ai/mmore.

cs.SE↗

arXiv2025

Towards Open Foundation Language Model and Corpus for Macedonian: A Low-Resource Language

The increase in technological adoption worldwide comes with demands for novel tools to be used by the general population. Large Language Models (LLMs) provide a great opportunity in this respect, but their capabilities remain limited for low-resource languages, restricting applications in countries where such languages are spoken. We create several resources to facilitate the adoption of LLMs and to support research advancements for Macedonian. We collect the largest Macedonian corpus to date, consisting of 40GB of textual data and totaling 3.5B words. To support conversational applications, we collect a 106k-instance instruction dataset, carefully built to be culturally grounded. For evaluation, we construct a Macedonian evaluation suite covering seven benchmarks. Finally, we train domestic-yak, a state-of-the-art 8B-parameter model, on our curated datasets and evaluate it against eight baseline models using the newly constructed benchmark suite. Our model outperforms all existing models in the 8B parameter range across all benchmarks, and achieves performance comparable to models up to 10x larger. Furthermore, a qualitative analysis with native speakers reveals that our model is preferred over larger counterparts, receiving higher ratings for grammatical correctness and cultural appropriateness. All datasets, code, and model weights are openly released, setting a foundation for advancing LLMs in similarly underrepresented languages. These resources are publicly available at github.com/LVSTCK for source code, and at huggingface.co/LVSTCK for pretrained model weights and data.

cs.CL↗

arXiv2023

A System for Differentiation of Schizophrenia and Bipolar Disorder based on rsfMRI

Schizophrenia and bipolar disorder are debilitating psychiatric illnesses that can be challenging to diagnose accurately. The similarities between the diseases make it difficult to differentiate between them using traditional diagnostic tools. Recently, resting-state functional magnetic resonance imaging (rsfMRI) has emerged as a promising tool for the diagnosis of psychiatric disorders. This paper presents several methods for differentiating schizophrenia and bipolar disorder based on features extracted from rsfMRI data. The system that achieved the best results, uses 1D Convolutional Neural Networks to analyze patterns of Intrinsic Connectivity time courses obtained from rsfMRI and potentially identify biomarkers that distinguish between the two disorders. We evaluate the system's performance on a large dataset of patients with schizophrenia and bipolar disorder and demonstrate that the system achieves a 0.7078 Area Under Curve (AUC) score in differentiating patients with these disorders. Our results suggest that rsfMRI-based classification systems have great potential for improving the accuracy of psychiatric diagnoses and may ultimately lead to more effective treatments for patients with this disorder.

eess.SP↗