Related papers: Anticipatory Planning for Multimodal AI Agents
In an unfamiliar setting, a model-based reinforcement learning agent can be limited by the accuracy of its world model. In this work, we present a novel, training-free approach to improving the performance of such agents separately from…
Reasoning models have recently shown remarkable progress in domains such as math and coding. However, their expert-level abilities in math and coding contrast sharply with their performance in long-horizon, interactive tasks such as web…
The development of state-of-the-art large language models is commonly understood as a two-stage process involving pre-training and post-training. We point out the need for an additional intermediate stage called reinforcement mid-training…
Large Language Models (LLMs) agents are increasingly pivotal for addressing complex tasks in interactive environments. Existing work mainly focuses on enhancing performance through behavior cloning from stronger experts, yet such approaches…
MLLMs have been successfully applied to multimodal embedding tasks, yet their generative reasoning capabilities remain underutilized. Directly incorporating chain-of-thought reasoning into embedding learning introduces two fundamental…
Multi-agent collaboration has emerged as a powerful paradigm for enhancing the reasoning capabilities of large language models, yet it suffers from interaction-level ambiguity that blurs generation, critique, and revision, making credit…
Video reasoning constitutes a comprehensive assessment of a model's capabilities, as it demands robust perceptual and interpretive skills, thereby serving as a means to explore the boundaries of model performance. While recent research has…
The development of autonomous agents for complex, long-horizon tasks is a central goal in AI. However, dominant training paradigms face a critical limitation: reinforcement learning (RL) methods that optimize solely for final task success…
The ReAct (Reasoning + Action) capability in large language models (LLMs) has become the foundation of modern agentic systems. Recent LLMs, such as DeepSeek-R1 and OpenAI o1/o3, exemplify this by emphasizing reasoning through the generation…
This paper proposes an intent-aware multi-agent planning framework as well as a learning algorithm. Under this framework, an agent plans in the goal space to maximize the expected utility. The planning process takes the belief of other…
In this work, we investigate how explicitly modeling problem's difficulty prior information shapes the effectiveness of reinforcement learning based fine-tuning for multimodal reasoning. Our exploration mainly comprises of following three…
Estimating uncertainty for AI agents in real-world multi-turn tool-using interaction with humans is difficult because failures are often triggered by sparse critical episodes (e.g., looping, incoherent tool use, or user-agent…
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…
While Large Language Models (LLMs) excel in certain reasoning tasks, they struggle in multi-agent games where the final outcome depends on the joint strategies of all agents. In multi-agent games, the non-stationarity of other agents brings…
Enhancing the temporal understanding of Multimodal Large Language Models (MLLMs) is essential for advancing long-form video analysis, enabling tasks such as temporal localization, action detection, and time-sensitive question answering.…
Traditional trajectory planning methods for autonomous vehicles have several limitations. For example, heuristic and explicit simple rules limit generalizability and hinder complex motions. These limitations can be addressed using…
Agentic search requires large language models (LLMs) to perform multi-step search to solve complex information-seeking tasks, imposing unique challenges on their reasoning capabilities. However, what constitutes effective reasoning for…
Multi-agent navigation in dynamic environments is of great industrial value when deploying a large scale fleet of robot to real-world applications. This paper proposes a decentralized partially observable multi-agent path planning with…
Temporal reasoning over long, multi-session dialogues is a critical capability for conversational agents. However, existing works and our pilot study have shown that as dialogue histories grow in length and accumulate noise, current…
Trajectory prediction has been a crucial task in building a reliable autonomous driving system by anticipating possible dangers. One key issue is to generate consistent trajectory predictions without colliding. To overcome the challenge, we…