arXiv preprints from January 1, 2026 through September 9, 2026 — 18:05:25 EST
Targeted and deliberate exploration of state--action pairs is essential in reward-free Markov Decision Problems (MDPs). More precisely, different state-action pairs exhibit different degree of importance or difficulty which must be actively and explicitly built into a controlled exploration strategy. To this end, we propose a weighted...
Agentic search has recently emerged as a powerful paradigm, where an agent interleaves multi-step reasoning with on-demand retrieval to solve complex questions. Despite its success, how to design a retriever for agentic search remains largely underexplored. Existing search agents typically rely on similarity-based retrievers, while...
In high-stakes domains like medicine, it may be generally desirable for models to faithfully adhere to the context provided. But what happens if the context does not align with model priors or safety protocols? In this paper, we investigate how LLMs behave and reason when presented with counterfactual (or even adversarial) medical...
Multi-modal entity alignment aims to identify equivalent entities between two multi-modal Knowledge graphs by integrating multi-modal data, such as images and text, to enrich the semantic representations of entities. However, existing methods may overlook the structural contextual information within each modality, making them...
Hard-label black-box attacks, relying solely on top-1 predictions, represent one of the most challenging yet practically threat models. Despite recent progress, existing approaches face two key limitations: (1) they overlook the critical role of initialization, focusing primarily on optimization strategies; and (2) they rely heavily...
Blind and low-vision (BLV) individuals face high unemployment rates. The job search is becoming harder as more employers use AI-driven systems to screen resumes before a human ever sees them. Such AI systems could inadvertently further disadvantage BLV job seekers, introducing additional barriers to an already difficult process. We...
Clustering is a long-standing research problem and a fundamental tool in AI and data analysis. The traditional k-center problem, a fundamental theoretical challenge in clustering, has a best possible approximation ratio of 2, and any improvement to a ratio of 2 - ε would imply P = NP. In this work, we study the constrained k-center...
Diffusion Transformers (DiT) have achieved milestones in synthesizing financial time-series data, such as stock prices and order flows. However, their performance in synthesizing treasury futures data is still underexplored. This work emphasizes the characteristics of treasury futures data, including its low volume, market...
There are 50 billion pieces of litter in the U.S. alone. Grass fields contribute to this problem because picnickers tend to leave trash on the field. We propose building a robot that can autonomously navigate, identify, and pick up trash in parks. To autonomously navigate the park, we used a Spanning Tree Coverage (STC) algorithm to...
This work bridges the fields of information retrieval and cultural analytics to support equitable access to historical knowledge. Using the British Library BL19 digital collection (more than 35,000 works from 1700-1899), we construct a benchmark for studying changes in language, terminology and retrieval in the 19th-century fiction...
Cross-lingual topic modeling seeks to uncover coherent and semantically aligned topics across languages - a task central to multilingual understanding. Yet most existing models learn topics in disjoint, language-specific spaces and rely on alignment mechanisms (e.g., bilingual dictionaries) that often fail to capture deep...
AI agents may soon become capable of autonomously completing valuable, long-horizon tasks in diverse domains. Current benchmarks either do not measure real-world tasks, or are not sufficiently difficult to meaningfully measure frontier models. To this end, we present Terminal-Bench 2.0: a carefully curated hard benchmark composed of...
We present a parallel algorithm for computing the minimum s-t cut in structured 3-dimensional proper order graphs arising from image segmentation problems. Proper order graphs are multi-column structures where vertices are arranged in parallel columns, with each vertex connected to consecutive vertices in adjacent columns. This graph...
Large Language Models (LLMs) have achieved high accuracy on medical question-answer (QA) benchmarks, yet their capacity for flexible clinical reasoning has been debated. Here, we asked whether advances in reasoning LLMs improve their cognitive flexibility in clinical reasoning. We assessed reasoning models from the OpenAI, Grok,...
While knowledge distillation has seen widespread use in pre-training and instruction tuning, its application to aligning language models with human preferences remains underexplored, particularly in the more realistic cross-tokenizer setting. The incompatibility of tokenization schemes between teacher and student models has largely...
To stabilize the training of Large Language Models (LLMs), gradient clipping is a nearly ubiquitous heuristic used to alleviate exploding gradients. However, traditional global norm clipping erroneously presupposes gradient homogeneity across different functional modules, leading to an adverse "spill-over" effect where volatile...
Retrieval-Augmented Generation systems depend on retrieving semantically relevant document chunks to support accurate, grounded outputs from large language models. In structured and repetitive corpora such as regulatory filings, chunk similarity alone often fails to distinguish between documents with overlapping language....
We extend the Rate-Distortion-Perception (RDP) framework to the Rényi information-theoretic regime, utilizing Sibson's $α$-mutual information to characterize the fundamental limits under distortion and perception constraints. For scalar Gaussian sources, we derive closed-form expressions for the Rényi RDP function, showing that the...
The evolution toward 6G networks increasingly relies on network slicing to provide tailored, End-to-End (E2E) logical networks over shared physical infrastructures. A critical challenge is effectively decomposing E2E Service Level Agreements (SLAs) into domain-specific SLAs, which current solutions handle through computationally...
Recent advances in task-oriented dialogue (TOD) systems, driven by large language models (LLMs) with extensive API and tool integration, have enabled conversational agents to coordinate interleaved goals, maintain long-horizon context, and act proactively through asynchronous execution. These capabilities extend beyond traditional TOD...
The increasing use of generative artificial intelligence (GenAI) in qualitative research raises important questions about analytic practice and interpretive authority. This study examines how researchers interact with an Inductive Thematic Analysis GPT (ITA-GPT), a purpose-built AI tool designed to support inductive thematic analysis...
As AI systems grow increasingly capable of operating for hours or days at a time, users' prompts are transforming into elaborate specifications for the AI to autonomously work on. While prompting for bounded, single-turn tasks has been extensively studied, less is known about how people communicate specifications for long-horizon...
We present results and analyses from the third VoicePrivacy Challenge held in 2024, which focuses on advancing voice anonymization technologies. The task was to develop a voice anonymization system for speech data that conceals a speaker's voice identity while preserving linguistic content and emotional state. We provide a systematic...
Dominating Set is a well-known combinatorial optimization problem which finds application in computational biology or mobile communication. Because of its $\mathrm{NP}$-hardness, one often turns to heuristics for good solutions. Many such heuristics have been empirically tested and perform rather well. However, it is not well...
Large Language Models (LLMs) have shown strong performance on code understanding tasks, yet they fundamentally lack the ability to perform precise, exhaustive mathematical reasoning about program behavior. Existing benchmarks either focus on mathematical proof automation, largely disconnected from real-world software, or on...