Related papers: TRACE: Trajectory-Aware Comprehensive Evaluation f…

A critical bottleneck in automating AI research is the execution of complex machine learning engineering (MLE) tasks. MLE differs from general software engineering due to computationally expensive evaluation (e.g., model training) and…

Trajectory representation learning (TRL) maps trajectories to vectors that can then be used for various downstream tasks, including trajectory similarity computation, trajectory classification, and travel-time estimation. However, existing…

Generalizing deep reinforcement learning agents to unseen environments remains a significant challenge. One promising solution is Unsupervised Environment Design (UED), a co-evolutionary framework in which a teacher adaptively generates…

Equipping Large Language Model (LLM) agents with domain-specific skills is critical for tackling complex tasks. Yet, manual authoring creates a severe scalability bottleneck. Conversely, automated skill generation often yields fragile or…

Large Reasoning Models (LRMs) increasingly rely on reasoning traces with complex internal structures. However, existing work lacks a unified answer to three fundamental questions: (1) what defines high-quality reasoning, (2) how to reliably…

The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling LRMs to reason longer, and more accurately. However, a growing body of studies show that…

This paper presents TRACE, a tool to analyze the quality of 2D embeddings generated through dimensionality reduction techniques. Dimensionality reduction methods often prioritize preserving either local neighborhoods or global distances,…

While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of \textit{execution efficiency} remains overlooked. We present \textbf{\textsc{trace}}, the first…

While Large Language Models (LLMs) have substantially improved the functional correctness of code translation, the critical dimension of \textit{execution efficiency} remains overlooked. We present \textbf{\textsc{trace}}, the first…

Evaluating AI agents that solve real-world tasks through function-call sequences remains an open challenge. Existing agentic benchmarks often reduce evaluation to a binary judgment of the final state, overlooking critical aspects such as…

As Reinforcement Learning (RL) agents are increasingly deployed in real-world applications, ensuring their behavior is transparent and trustworthy is paramount. A key component of trust is explainability, yet much of the work in Explainable…

For users navigating travel e-commerce websites, the process of researching products and making a purchase often results in intricate browsing patterns that span numerous sessions over an extended period of time. The resulting clickstream…

Constructing valid and informative conformal prediction regions for multi-dimensional outputs remains a fundamental challenge. While conformal prediction provides finite-sample, distribution-free coverage guarantees, its practical…

Retrieval-Augmented Generation (RAG) shows promise for enterprise knowledge work, yet it often underperforms in high-stakes decision settings that require deep synthesis, strict traceability, and recovery from underspecified prompts.…

Retrieval-augmented generation (RAG) offers an effective approach for addressing question answering (QA) tasks. However, the imperfections of the retrievers in RAG models often result in the retrieval of irrelevant information, which could…

Despite their success and widespread adoption, the opaque nature of deep neural networks (DNNs) continues to hinder trust, especially in critical applications. Current interpretability solutions often yield inconsistent or oversimplified…

Failure attribution, i.e., identifying the responsible agent and decisive step of a failure, is particularly challenging in LLM-based multi-agent systems (MAS) due to their natural-language reasoning, nondeterministic outputs, and intricate…

Traditional conversational travel recommender systems primarily optimize for user relevance and convenience, often reinforcing popular, overcrowded destinations and carbon-intensive travel choices. To address this, we present TRACE (Tourism…

Deep Research Agents (DRAs) aim to solve complex, long-horizon research tasks involving planning, retrieval, multimodal understanding, and report generation, yet their evaluation remains challenging due to dynamic web environments and…

As an embodiment of intelligence evolution toward interconnected architectures, Deep Research Agents (DRAs) systematically exhibit the capabilities in task decomposition, cross-source retrieval, multi-stage reasoning, information…