Search results

By learning the idiosyncrasies of accumulated layers of legacy systems, AI agents can preserve institutional knowledge and provide a unified interface to a range of services.

Agentic vision–language models are increasingly trained to 'think with images' by calling image operations. However, we show that high final-answer accuracy often hides unfaithful visual reasoning: models may invoke tools on irrelevant regions or ignore tool outputs entirely, yet still guess the correct answer. In this work, we first propose a faithfulness evaluation protocol that measures whether intermediate

Generating long, coherent text remains a challenge for large language models (LLMs), as they lack hierarchical planning and structured organization in discourse generation. We introduce Structural Alignment, a novel method that aligns LLMs with human-like discourse structures to enhance long-form text generation. By integrating linguistically grounded discourse frameworks into reinforcement learning, our

Conversational agents have become ubiquitous across application domains, such as, shopping assistants, medical diagnosis, autonomous task planning etc. Users interacting with these agents often fail to understand how to start a conversation or what to ask next to obtain the desired information. To enable seamless and hassle-free user-agent interactions, we introduce Next Question Suggestions (NQS), which

Reinforcement learning with verifiable rewards has significantly advanced reasoning with large language models (LLMs) in domains such as mathematics and logic. However, verifiable signals provide only coarse-grained or binary correctness feedback. This limitation results in inefficiencies like overly verbose or repetitive reasoning. Existing length-based solutions (e.g., length penalty) compromise accuracy

Recent advances in generative retrieval allow large language models (LLMs) to recommend items by generating their identifiers token by token. This requires each item to be represented by a compact, semantically meaningful sequence of tokens that an LLM can understand. We introduce a method to generate multimodal music token (3MToken) that transforms rich metadata from a music database—including audio, credits

Predictive modeling over relational databases (RDBs) powers applications in various domains, yet remains challenging due to the need to capture both cross-table dependencies and complex feature interactions. Recent Relational Deep Learning (RDL) methods automate feature engineering via message passing, while classical approaches like Deep Feature Synthesis (DFS) rely on predefined non-parametric aggregators

Large Language Models (LLMs) can serve as world models to enhance agent decision-making in digital environments by simulating future states and predicting action outcomes, potentially eliminating costly trial-and-error exploration. However, this capability is fundamentally limited by LLM's tendency to hallucination and their reliance on static training knowledge, which could lead to compounding errors that

Large language models (LLMs) are increasingly deployed in real-world applications such as chatbots, writing assistants, and text summarization tools. As these applications become more central to user-facing tasks, robust evaluation of their performance becomes critical, not only for ensuring quality but also for guiding continuous improvement. Traditional evaluation approaches rely on intrinsic metrics

As AI agents become more autonomous, the key challenge isn't what they can do; it's how to design the human side of the equation.

What machine learning theorists learned using AI agents to generate proofs — and what comes next.

As AI models grow larger, they become less insightful, not more. To ensure that they continue to learn, we need to reduce their inference time.

Product information extraction is crucial for e-commerce services, but obtaining high-quality labeled datasets remains challenging. We present a systematic approach for generating synthetic e-commerce product data using Large Language Models (LLMs), introducing a controlled modification framework with three strategies: attribute-preserving modification, controlled negative example generation, and systematic

Large Language Model (LLM) judges exhibit strong reasoning capabilities but are limited to textual content. This leaves current automatic Speech-to-Speech (S2S) evaluation methods reliant on opaque and expensive Audio Language Models (ALMs). In this work, we propose TRACE (Textual Reasoning over Audio Cues for Evaluation), a novel framework that enables LLM judges to reason over audio cues to achieve cost-efficient

Large Language Models (LLMs) suffer from severe catastrophic forgetting when adapted sequentially to new tasks in a continual learning (CL) setting. Existing approaches are fundamentally limited: replay-based methods are impractical and could potentially violate privacy, while strict orthogonality-based methods collapse under scale: each new task is projected onto an orthogonal complement, progressively

Reinforcement learning (RL) has re-emerged as a natural approach for training interactive LLM agents in real-world environments. However, directly applying the widely used Group Relative Policy Optimization (GRPO) algorithm to multi-turn tasks exposes notable limitations, particularly in scenarios requiring long-horizon reasoning. To address these challenges, we investigate more stable and effective advantage