Towards bandit-based prompt-tuning for in-the-wild foundation agents

Prompting has emerged as the dominant paradigm for adapting large, pre-trained transformer-based models to downstream tasks. The Prompting Decision Transformer (PDT) enables large-scale, multi-task offline reinforcement learning pre-training by leveraging stochastic trajectory prompts to identify the target task. However, these prompts are sampled uniformly from expert demonstrations, overlooking a critical limitation: Not all prompts are equally informative for differentiating between tasks. To address this, we propose an inference time bandit-based prompt-tuning framework that explores and optimizes trajectory prompt selection to enhance task performance. Our experiments indicate not only clear performance gains due to bandit-based prompt-tuning, but also better sample complexity, scalability, and prompt space exploration compared to prompt-tuning baselines.

Enhancing Pre-Trained Decision Transformers with Prompt-Tuning Bandits

Harnessing large offline datasets is vital for training foundation models that can generalize across diverse tasks. Offline Reinforcement Learning (RL) offers a powerful framework for these scenarios, enabling the derivation of optimal policies even from suboptimal data. The Prompting Decision Transformer (PDT) is an offline RL multi-task model that distinguishes tasks through stochastic trajectory prompts, which are task-specific tokens maintained in context during rollouts. However, PDT samples these tokens uniformly at random from per-task demonstration datasets, failing to account for differences in token informativeness and potentially leading to performance degradation. To address this limitation, we introduce a scalable bandit-based prompt-tuning method that dynamically learns to construct high-performance trajectory prompts. Our approach significantly enhances downstream task performance without modifying the pre-trained Transformer backbone. Empirical results on benchmark tasks and a newly designed multi-task environment demonstrate the effectiveness of our method, creating a seamless bridge between general multi-task offline pre-training and task-specific online adaptation.

On the Power of Heuristics in Temporal Graphs

Dynamic graph datasets often exhibit strong temporal patterns, such as recency, which prioritizes recent interactions, and popularity, which favors frequently occurring nodes. We demonstrate that simple heuristics leveraging only these patterns can perform on par or outperform state-of-the-art neural network models under standard evaluation protocols. To further explore these dynamics, we introduce metrics that quantify the impact of recency and popularity across datasets. Our experiments on BenchTemp and the Temporal Graph Benchmark show that our approaches achieve state-of-the-art performance across all datasets in the latter and secure top ranks on multiple datasets in the former. These results emphasize the importance of refined evaluation schemes to enable fair comparisons and promote the development of more robust temporal graph models. Additionally, they reveal that current deep learning methods often struggle to capture the key patterns underlying predictions in real-world temporal graphs. For reproducibility, we have made our code publicly available.

Unified Approaches in Self-Supervised Event Stream Modeling: Progress and Prospects

The proliferation of digital interactions across diverse domains, such as healthcare, e-commerce, gaming, and finance, has resulted in the generation of vast volumes of event stream (ES) data. ES data comprises continuous sequences of timestamped events that encapsulate detailed contextual information relevant to each domain. While ES data holds significant potential for extracting actionable insights and enhancing decision-making, its effective utilization is hindered by challenges such as the scarcity of labeled data and the fragmented nature of existing research efforts. Self-Supervised Learning (SSL) has emerged as a promising paradigm to address these challenges by enabling the extraction of meaningful representations from unlabeled ES data. In this survey, we systematically review and synthesize SSL methodologies tailored for ES modeling across multiple domains, bridging the gaps between domain-specific approaches that have traditionally operated in isolation. We present a comprehensive taxonomy of SSL techniques, encompassing both predictive and contrastive paradigms, and analyze their applicability and effectiveness within different application contexts. Furthermore, we identify critical gaps in current research and propose a future research agenda aimed at developing scalable, domain-agnostic SSL frameworks for ES modeling. By unifying disparate research efforts and highlighting cross-domain synergies, this survey aims to accelerate innovation, improve reproducibility, and expand the applicability of SSL to diverse real-world ES challenges.

Expressivity of Representation Learning on Continuous-Time Dynamic Graphs: An Information-Flow Centric Review

Graphs are ubiquitous in real-world applications, ranging from social networks to biological systems, and have inspired the development of Graph Neural Networks (GNNs) for learning expressive representations. While most research has centered on static graphs, many real-world scenarios involve dynamic, temporally evolving graphs, motivating the need for Continuous-Time Dynamic Graph (CTDG) models. This paper provides a comprehensive review of Graph Representation Learning (GRL) on CTDGs with a focus on Self-Supervised Representation Learning (SSRL). We introduce a novel theoretical framework that analyzes the expressivity of CTDG models through an Information-Flow (IF) lens, quantifying their ability to propagate and encode temporal and structural information. Leveraging this framework, we categorize existing CTDG methods based on their suitability for different graph types and application scenarios. Within the same scope, we examine the design of SSRL methods tailored to CTDGs, such as predictive and contrastive approaches, highlighting their potential to mitigate the reliance on labeled data. Empirical evaluations on synthetic and real-world datasets validate our theoretical insights, demonstrating the strengths and limitations of various methods across long-range, bi-partite and community-based graphs. This work offers both a theoretical foundation and practical guidance for selecting and developing CTDG models, advancing the understanding of GRL in dynamic settings.

Understanding Players as if They Are Talking to the Game in a Customized Language: A Pilot Study

This pilot study explores the application of language models (LMs) to model game event sequences, treating them as a customized natural language. We investigate a popular mobile game, transforming raw event data into textual sequences and pretraining a Longformer model on this data. Our approach captures the rich and nuanced interactions within game sessions, effectively identifying meaningful player segments. The results demonstrate the potential of self-supervised LMs in enhancing game design and personalization without relying on ground-truth labels.

Behavior Structformer: Learning Players Representations with Structured Tokenization

In this paper, we introduce the Behavior Structformer, a method for modeling user behavior using structured tokenization within a Transformer-based architecture. By converting tracking events into dense tokens, this approach enhances model training efficiency and effectiveness. We demonstrate its superior performance through ablation studies and benchmarking against traditional tabular and semi-structured baselines. The results indicate that structured tokenization with sequential processing significantly improves behavior modeling.

Kotlin ML Pack: Technical Report

In this technical report, we present three novel datasets of Kotlin code: KStack, KStack-clean, and KExercises. We also describe the results of fine-tuning CodeLlama and DeepSeek models on this data. Additionally, we present a version of the HumanEval benchmark rewritten by human experts into Kotlin - both the solutions and the tests. Our results demonstrate that small, high-quality datasets (KStack-clean and KExercises) can significantly improve model performance on code generation tasks, achieving up to a 16-point increase in pass rate on the HumanEval benchmark. Lastly, we discuss potential future work in the field of improving language modeling for Kotlin, including the use of static analysis tools in the learning process and the introduction of more intricate and realistic benchmarks.

player2vec: A Language Modeling Approach to Understand Player Behavior in Games

Methods for learning latent user representations from historical behavior logs have gained traction for recommendation tasks in e-commerce, content streaming, and other settings. However, this area still remains relatively underexplored in video and mobile gaming contexts. In this work, we present a novel method for overcoming this limitation by extending a long-range Transformer model from the natural language processing domain to player behavior data. We discuss specifics of behavior tracking in games and propose preprocessing and tokenization approaches by viewing in-game events in an analogous way to words in sentences, thus enabling learning player representations in a self-supervised manner in the absence of ground-truth annotations. We experimentally demonstrate the efficacy of the proposed approach in fitting the distribution of behavior events by evaluating intrinsic language modeling metrics. Furthermore, we qualitatively analyze the emerging structure of the learned embedding space and show its value for generating insights into behavior patterns to inform downstream applications.

Rooms with Text: A Dataset for Overlaying Text Detection

In this paper, we introduce a new dataset of room interior pictures with overlaying and scene text, totalling to 4836 annotated images in 25 product categories. We provide details on the collection and annotation process of our dataset, and analyze its statistics. Furthermore, we propose a baseline method for overlaying text detection, that leverages the character region-aware text detection framework to guide the classification model. We validate our approach and show its efficiency in terms of binary classification metrics, reaching the final performance of 0.95 F1 score, with false positive and false negative rates of 0.02 and 0.06 correspondingly.