Related papers: Co-ReAct: Rubrics as Step-Level Collaborators for …

LLM-driven multi-agent frameworks address complex reasoning tasks through multi-role collaboration. However, existing approaches often suffer from reasoning instability, where individual agent errors are amplified through collaboration,…

Referring Expression Comprehension and Segmentation are critical tasks for assessing the integration of language understanding and image comprehension, serving as benchmarks for Multimodal Large Language Models (MLLMs) capabilities. To…

Multimodal Large Language Models (MLLMs) have powered Graphical User Interface (GUI) Agents, showing promise in automating tasks on computing devices. Recent works have begun exploring reasoning in GUI tasks with encouraging results.…

Agentic Reinforcement Learning (Agentic RL) has achieved notable success in enabling agents to perform complex reasoning and tool use. However, most methods still relies on sparse outcome-based reward for training. Such feedback fails to…

In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately. Most of the…

Recent advances in LLM agents have largely built on reasoning backbones like ReAct, which interleave thought and action in complex environments. However, ReAct often produces ungrounded or incoherent reasoning steps, leading to misalignment…

Causal analysis plays a foundational role in scientific discovery and reliable decision-making, yet it remains largely inaccessible to domain experts due to its conceptual and algorithmic complexity. This disconnect between causal…

Large language models (LLMs) are increasingly used as autonomous agents, tackling tasks from robotics to web navigation. Their performance depends on the underlying base agent. Existing methods, however, struggle with long-context reasoning…

Deep neural networks have emerged as a powerful technique for learning representations from user-item interaction data in collaborative filtering (CF) for recommender systems. However, many existing methods heavily rely on unique user and…

Agentic multimodal models have garnered significant attention for their ability to leverage external tools to tackle complex tasks. However, it is observed that such agents often meet premature interaction collapse, caused by two primary…

Generating natural language explanations for recommendations has become increasingly important in recommender systems. Traditional approaches typically treat user reviews as ground truth for explanations and focus on improving review…

Retrieval-Augmented Generation (RAG) enhances language models by retrieving and incorporating relevant external knowledge. However, traditional retrieve-and-generate processes may not be optimized for real-world scenarios, where queries…

Language agents have achieved considerable performance on various complex question-answering tasks by planning with external tools. Despite the incessant exploration in this field, existing language agent systems still struggle with costly,…

When an LLM-based agent improves on a task, is the gain from the model itself or from the reasoning paradigm wrapped around it? We study this question by comparing six inference-time paradigms, namely Direct, CoT, ReAct, Plan-Execute,…

Complex reasoning in tool-augmented agent frameworks is inherently long-horizon, causing reasoning traces and transient tool artifacts to accumulate and strain the bounded working context of large language models. Without explicit memory…

With the growing popularity of LLM agents and RAG, it has become increasingly important to retrieve documents that are essential for solving a task, even when their connection to the task is indirect or implicit. Addressing this problem…

Large Language Models (LLMs) have demonstrated potential in automating scientific ideation, yet current approaches relying on iterative prompting or complex multi-agent architectures often suffer from hallucination or computational…

Information-seeking is a core capability for AI agents, requiring them to gather and reason over tool-generated information across long trajectories. However, such multi-step information-seeking tasks remain challenging for agents backed by…

Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analytical perspectives needed vary across samples due to the diversity of sarcastic…

When estimating the relevancy between a query and a document, ranking models largely neglect the mutual information among documents. A common wisdom is that if two documents are similar in terms of the same query, they are more likely to…