Related papers: AlphaApollo: A System for Deep Agentic Reasoning

We study what actually works and what doesn't for training large language models as agents via multi-turn reinforcement learning. Despite rapid progress, existing frameworks and definitions are fragmented, and there is no systematic…

Multimodal reasoning has emerged as a powerful framework for enhancing reasoning capabilities of reasoning models. While multi-turn table reasoning methods have improved reasoning accuracy through tool use and reward modeling, they rely on…

Large Language Model(LLM)-based agents have shown strong capabilities in web information seeking, with reinforcement learning (RL) becoming a key optimization paradigm. However, planning remains a bottleneck, as existing methods struggle…

While current Multimodal Large Language Models (MLLMs) have demonstrated proficiency in reasoning tasks such as mathematics and logic, their capacity for long-chain reflective reasoning, a prerequisite for solving complex real-world…

Augmented Language Models (ALMs) blend the reasoning capabilities of Large Language Models (LLMs) with tools that allow for knowledge retrieval and action execution. Existing ALM systems trigger LLM thought processes while pulling…

What does it mean to plan? Current agentic systems, whether scaffolded workflows or end-to-end policies, rely on reactive decision-making: selecting the next action via a fixed procedure with at most undifferentiated adaptive computation…

This survey paper examines the recent advancements in AI agent implementations, with a focus on their ability to achieve complex goals that require enhanced reasoning, planning, and tool execution capabilities. The primary objectives of…

Reasoning has emerged as a pivotal capability in Large Language Models (LLMs). Through Reinforcement Learning (RL), typically Group Relative Policy Optimization (GRPO), these models are able to solve complex tasks such as mathematics and…

Advancing complex reasoning in large language models relies on high-quality, verifiable datasets, yet human annotation remains cost-prohibitive and difficult to scale. Current synthesis paradigms often face a recurring trade-off:…

Multimodal Large Language Models (MLLMs) are powerful at integrating diverse data, but they often struggle with complex reasoning. While Reinforcement learning (RL) can boost reasoning in LLMs, applying it to MLLMs is tricky. Common issues…

Large language models hold promise as scientific assistants, yet existing agents either rely solely on algorithm evolution or on deep research in isolation, both of which face critical limitations. Pure algorithm evolution, as in…

Failure attribution in multi-agent systems -- pinpointing the exact step where a decisive error occurs -- is a critical yet unsolved challenge. Current methods treat this as a pattern recognition task over long conversation logs, leading to…

Direct prompt-based editing often fails on complex transformations because vague and subjective prompts often require nuanced understanding of what should be changed in the image. Our core intuition is that leveraging compositional image…

Enhancing LLMs with the ability to actively search external knowledge is crucial for complex and real-world tasks. Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance…

We introduce ApolloRL, an open platform for research in reinforcement learning for autonomous driving. The platform provides a complete closed-loop pipeline with training, simulation, and evaluation components. It comes with 300 hours of…

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…

Multi-agent systems built from prompted large language models can improve multi-round reasoning, yet most existing pipelines rely on fixed, trajectory-wide communication patterns that are poorly matched to the stage-dependent needs of…

Time series reasoning treats time as a first-class axis and incorporates intermediate evidence directly into the answer. This survey defines the problem and organizes the literature by reasoning topology with three families: direct…

This paper presents AlphaOne ($\alpha$1), a universal framework for modulating reasoning progress in large reasoning models (LRMs) at test time. $\alpha$1 first introduces $\alpha$ moment, which represents the scaled thinking phase with a…

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for…