Related papers: EvolveRouter: Co-Evolving Routing and Prompt for M…
While reasoning-augmented large language models (RLLMs) significantly enhance complex task performance through extended reasoning chains, they inevitably introduce substantial unnecessary token consumption, particularly for simpler problems…
Chain-of-thought has been proven essential for enhancing the complex reasoning abilities of Large Language Models (LLMs), but it also leads to high computational costs. Recent advances have explored the method to route queries among…
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…
As AI moves beyond text, large language models (LLMs) increasingly power vision, audio, and document understanding; however, their high inference costs hinder real-time, scalable deployment. Conversely, smaller open-source models offer cost…
Co-designing autonomous robotic agents involves simultaneously optimizing the controller and physical design of the agent. Its inherent bi-level optimization formulation necessitates an outer loop design optimization driven by an inner loop…
Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixed: stored content evolves while scoring functions, fusion strategies, and…
As Large Language Models (LLMs) are increasingly deployed as autonomous agents, they face a critical scalability bottleneck known as the "Generalization-Specialization Dilemma." Monolithic agents equipped with extensive toolkits suffer from…
Large-scale online ride-sharing platforms have substantially transformed our lives by reallocating transportation resources to alleviate traffic congestion and promote transportation efficiency. An efficient fleet management strategy not…
Fine-tuning pre-trained language models, particularly large language models, demands extensive computing resources and can result in varying performance outcomes across different domains and datasets. This paper examines the approach of…
Visual Question Answering (VQA) requires models to identify the correct answer options based on both visual and textual evidence. Recent Mixture-of-Experts (MoE) methods improve option reasoning by grouping similar concepts or routing based…
Multi-agent reasoning has shown promise for improving the problem-solving ability of large language models by allowing multiple agents to explore diverse reasoning paths. However, most existing multi-agent methods rely on inference-time…
While recent autonomous agents demonstrate impressive capabilities, they predominantly rely on manually scripted workflows and handcrafted heuristics, inherently limiting their potential for open-ended improvement. To address this, we…
We propose a method that allows to develop shared understanding between two agents for the purpose of performing a task that requires cooperation. Our method focuses on efficiently establishing successful task-oriented communication in an…
In numerous artificial intelligence applications, the collaborative efforts of multiple intelligent agents are imperative for the successful attainment of target objectives. To enhance coordination among these agents, a distributed…
Research on Reinforcement Learning (RL) approaches for discrete optimization problems has increased considerably, extending RL to areas classically dominated by Operations Research (OR). Vehicle routing problems are a good example of…
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…
Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted planning structures that lack the flexibility to adapt to…
LLM agents achieve strong performance on complex reasoning tasks but incur high latency and compute cost. In practice, many queries fall within the capability boundary of cutting-edge LLMs and do not require full agent execution, making…
Achieving general-purpose robotics requires empowering robots to adapt and evolve based on their environment and feedback. Traditional methods face limitations such as extensive training requirements, difficulties in cross-task…
Large language models (LLMs) have demonstrated exceptional performance across a wide range of natural language tasks. However, selecting the optimal LLM to respond to a user query often necessitates a delicate balance between performance…