Related papers: AdaTIR: Adaptive Tool-Integrated Reasoning via Dif…

Large Language Models (LLMs) can extend their parameter knowledge limits by adopting the Tool-Integrated Reasoning (TIR) paradigm. However, existing LLM-based agent training framework often focuses on answers' accuracy, overlooking specific…

Vision-language agents that orchestrate specialized tools for image restoration (IR) have emerged as a promising method, yet most existing frameworks operate in a training-free manner. They rely on heuristic task scheduling and exhaustive…

Modern Augmented reality applications require performing multiple tasks on each input frame simultaneously. Multi-task learning (MTL) represents an effective approach where multiple tasks share an encoder to extract representative features…

The frontier of visual reasoning is shifting toward models like OpenAI o3, which can intelligently create and operate tools to transform images for problem-solving, also known as thinking-\textit{with}-images in chain-of-thought. Yet…

Effective tool use is essential for agentic AI, yet training agents to utilize tools remains challenging due to manually designed rewards, limited training data, and poor multi-tool selection, resulting in slow adaptation, wasted…

Large Language Models (LLMs) have demonstrated remarkable capabilities but often face challenges with tasks requiring sophisticated reasoning. While Chain-of-Thought (CoT) prompting significantly enhances reasoning, it indiscriminately…

We introduce Agentic Reasoning, a framework that enhances large language model (LLM) reasoning by integrating external tool-using agents. Agentic Reasoning dynamically leverages web search, code execution, and structured memory to address…

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…

The inherent capabilities of a language model (LM) and the reasoning strategies it employs jointly determine its performance in reasoning tasks. While test-time scaling is regarded as an effective approach to tackling complex reasoning…

We present an agentic framework, Thinker, which achieves state of art performance in challenging reasoning tasks for realistic customer service scenarios that involve complex business logic and human interactions via long horizons. On the…

Fair workload enforcement in heterogeneous multi-agent systems that pursue shared objectives remains challenging. Fixed fairness penalties often introduce inefficiencies, training instability, and conflicting agent incentives.…

Traditional workflow-based agents exhibit limited intelligence when addressing real-world problems requiring tool invocation. Tool-integrated reasoning (TIR) agents capable of autonomous reasoning and tool invocation are rapidly emerging as…

Large-scale reinforcement learning with verifiable rewards (RLVR) has demonstrated its effectiveness in harnessing the potential of large language models (LLMs) for single-turn reasoning tasks. In realistic reasoning scenarios, LLMs can…

Recent advancements in large language models (LLMs) have been remarkable. Users face a choice between using cloud-based LLMs for generation quality and deploying local-based LLMs for lower computational cost. The former option is typically…

Large reasoning models (LRMs) achieve impressive reasoning capabilities by generating lengthy chain-of-thoughts, but this "overthinking" incurs high latency and cost without commensurate accuracy gains. In this work, we introduce AALC, a…

Recent advances in Large Language Models (LLMs) demonstrate that chain-of-thought prompting and deep reasoning substantially enhance performance on complex tasks, and multi-agent systems can further improve accuracy by enabling model…

We introduce ToRL (Tool-Integrated Reinforcement Learning), a framework for training large language models (LLMs) to autonomously use computational tools via reinforcement learning. Unlike supervised fine-tuning, ToRL allows models to…

Verifiers have been demonstrated to enhance LLM reasoning via test-time scaling (TTS). Yet, they face significant challenges in complex domains. Error propagation from incorrect intermediate reasoning can lead to false positives for…

The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security…

Enabling agentic AI systems to adapt their problem-solving approaches based on post-training interactions remains a fundamental challenge. While systems that update and maintain a memory at inference time have been proposed, existing…