arXiv subjects

Ante Kapetanovic

Publications and source records attributed to Ante Kapetanovic.

6 recordsLinked to original sources

arXiv2026

A Phased Workflow for Operating LLM-Based Coding Agents

LLM-based coding agents combine a foundation model with a harness that shapes agent behavior. For non-trivial tasks, how practitioners structure their work with the coding agents determines whether reliable results follow. We report on a phased workflow for operating coding agents developed by the AI research team at Infobip. The workflow structures agent-assisted development into four phases where human effort is front-loaded and delegation increases as artifacts mature. Context management is the central concern, addressed through four strategies applied at each phase to counter known failure modes. From practitioner experience, we observe that upstream errors in research and planning can compound across later phases, while correcting generated code can introduce bloat and fragility. This motivates front-loading human review. We identify two open problems: the absence of metrics for workflow effectiveness and the gap between formalized context management components and the workflow-level patterns that practitioners need.

cs.SE↗

arXiv2026

Retrieval, Scoring, and Decoding Shape Performance and Stability in LLM-based Conversational Recommendation

Large language models (LLMs) are increasingly used as rerankers in conversational recommender systems, yet measured gains depend strongly on the retrieval and inference protocol. On the ReDial conversational movie recommendation benchmark, we compare proprietary, open-weight, and fine-tuned LLM rerankers with collaborative-filtering and sequential baselines in a shared retrieve-then-rerank pipeline. We vary candidate-pool size, first-stage retriever, and decoding temperature. With a shared semantic top-250 candidate pool and strict candidate-aware scoring, the best proprietary reranker reaches NDCG@10 of 0.1497, compared with 0.0939 for the strongest non-LLM baseline. The same reranker reaches 0.2925 in zero-shot generation, showing that unconstrained scoring can yield a much larger apparent advantage than matched-pool evaluation. No evaluated open-weight LLM outperforms the tuned shallow autoencoder baseline under this protocol. For the strongest proprietary and open-weight rerankers, switching from semantic to collaborative-filtering candidates raises NDCG@10 by more than 50%, showing that measured reranker performance is highly sensitive to candidate generation. For the best proprietary reranker, raising temperature from 0 to 1.0 increases top-10 Jaccard distance from 0.0900 to 0.1240 while mean NDCG@10 changes negligibly, whereas weaker LLMs show larger degradation. These ReDial results support treating candidate generation, candidate-pool size, scoring policy, and decoding configuration as required reporting fields rather than implementation details.

cs.CL↗

arXiv2026

Conversational Recommendation over Live E-Commerce Catalogues with Self-Refreshing Retrieval

Conversational recommender systems based on large language models (LLMs) are usually evaluated on static, pre-indexed item collections, yet e-commerce catalogues change continuously as products are added or removed, repriced, and restocked. We present a merchant-agnostic, multi-turn conversational shopping assistant that operates over such live catalogues. Its central component is a self-refreshing retriever that ingests a merchant product feed, enriches the records, and synchronizes them into a vector index. On each run, per-item hashes identify which products are new, changed, deleted, or unchanged, so only the delta is processed rather than rebuilding the whole catalogue. A controller-based dialogue layer consumes this index, using an LLM only for intent classification and preference elicitation while retrieval, reranking, and diversity selection run as dedicated functions. Our demonstration is a WhatsApp shopping assistant in which catalogue changes reach the recommendations after the next successful sync. A live chatbot, documentation, and a recorded walkthrough are available at https://github.com/infobip/infobip-agentic-crs.

cs.IR↗

arXiv2026

Anchoring Bias in LLM-as-a-Judge Systems: Prior Scores Compromise Evaluation Independence

Large language models (LLMs) increasingly assess generated content, giving rise to the LLM-as-a-Judge paradigm. These systems now score outputs, filter content, and gate iterative refinement in production pipelines, where each judgment is often assumed to be independent of earlier evaluations. We test this assumption using three prompt conditions: no metadata, revision framing, and anchored metadata containing revision, attempt, and prior-score fields. We show that prior scores, even when included only as context metadata, anchor judgments and systematically shift ratings toward their values. Across 192,000 attempted evaluations (185,271 successful), seven out of the eight evaluated models have 95% task-stratified bootstrap intervals below zero for the total anchored-metadata effect on 20 fixed texts. Cohen's $d$, a standardized measure of the difference between score distributions, reaches an absolute value of 0.71. Token-level analysis of selected model-task probes suggests a threshold-like response pattern: introducing anchored metadata produces a marked redistribution of output-score probabilities, while changing the anchor value within the tested below-threshold range produces comparatively little additional variation. On categorical industry data with human-labeled ground truth, anchored metadata blocks 48% of error corrections and flips 10.18% of correct judgments toward an assigned wrong label, demonstrating the bias extends beyond numerical scoring to categorical decisions. Neither Chain-of-Thought nor a metadata-disregard warning reduces the total effect, although the warning improves the paired accuracy effect relative to baseline in the industry experiment. Reliable LLM evaluation demands careful context engineering rather than an assumption of impartiality. Effective mitigation must be validated for the intended model and task or domain.

cs.CL↗

arXiv2026

Comparative Analysis of Modern Machine Learning Models for Retail Sales Forecasting

Accurate demand forecasting is critical for brick-and-mortar retailers to optimize inventory management and minimize costs. This study evaluates statistical baselines, tree-based ensembles (XGBoost and LightGBM), and deep learning architectures (N-BEATS, N-HiTS, and the Temporal Fusion Transformer) on retail sales data characterized by intermittent demand, substantial missingness, and frequent product turnover. Models are compared across four configurations varying by aggregation level and imputation strategy, using evaluation protocols that reflect typical deployment patterns for each model class. Localized tree-based methods achieve superior performance, with XGBoost attaining the lowest RMSE of 4.833. While SAITS-based imputation improved neural network performance in aggregated settings, these models remained inferior to ensemble methods. The results suggest that, under the studied constraints, model selection should prioritize alignment with problem characteristics over architectural sophistication.

cs.LG↗

arXiv2023

Standardized Benchmark Dataset for Localized Exposure to a Realistic Source at 10$-$90 GHz

The lack of freely available standardized datasets represents an aggravating factor during the development and testing the performance of novel computational techniques in exposure assessment and dosimetry research. This hinders progress as researchers are required to generate numerical data (field, power and temperature distribution) anew using simulation software for each exposure scenario. Other than being time consuming, this approach is highly susceptible to errors that occur during the configuration of the electromagnetic model. To address this issue, in this paper, the limited available data on the incident power density and resultant maximum temperature rise on the skin surface considering various steady-state exposure scenarios at 10$-$90 GHz have been statistically modeled. The synthetic data have been sampled from the fitted statistical multivariate distribution with respect to predetermined dosimetric constraints. We thus present a comprehensive and open-source dataset compiled of the high-fidelity numerical data considering various exposures to a realistic source. Furthermore, different surrogate models for predicting maximum temperature rise on the skin surface were fitted based on the synthetic dataset. All surrogate models were tested on the originally available data where satisfactory predictive performance has been demonstrated. A simple technique of combining quadratic polynomial and tensor-product spline surrogates, each operating on its own cluster of data, has achieved the lowest mean absolute error of 0.058 °C. Therefore, overall experimental results indicate the validity of the proposed synthetic dataset.

physics.med-ph↗