Related papers: SGA-MCTS: Decoupling Planning from Execution via T…

Monte Carlo Tree Search (MCTS) is a widely used approach for policy improvement through search with increasing popularity for real world applications. Due to the sequential and deterministic nature of its search, runtime-scaling of MCTS…

Large language models (LLMs) have demonstrated exceptional potential in complex reasoning,pioneering a new paradigm for autonomous agent decision making in dynamic settings. However, in Real-Time Strategy (RTS) scenarios, LLMs suffer from a…

Current literature, aiming to surpass the "Chain-of-Thought" approach, often resorts to external modi operandi involving halting, modifying, and then resuming the generation process to boost Large Language Models' (LLMs) reasoning…

Research on LLM technologies is rapidly emerging, with most of them employ a 'fast thinking' approach to inference. Most LLMs generate the final result based solely on a single query and LLM's reasoning capabilities. However, with the…

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…

Symbolic regression aims to discover concise, interpretable mathematical expressions that satisfy desired objectives, such as fitting data, posing a highly combinatorial optimization problem. While genetic programming has been the dominant…

Retrieval-augmented generation (RAG) substantially extends the knowledge boundary of large language models. However, it still faces two major challenges when handling complex reasoning tasks: low context utilization and frequent…

In this work, we consider the popular tree-based search strategy within the framework of reinforcement learning, the Monte Carlo Tree Search (MCTS), in the context of infinite-horizon discounted cost Markov Decision Process (MDP). While…

Vision-Language-Action models (VLAs) achieve strong performance in general robotic manipulation tasks by scaling imitation learning. However, existing VLAs are limited to predicting short-sighted next-action, which struggle with…

Recent advances in test-time scaling have shown promising results in improving Large Language Model (LLM) performance through strategic computation allocation during inference. While this approach has demonstrated strong improvements in…

To solve the problem of lateral and logitudinal joint decision-making of multi-vehicle cooperative driving for connected and automated vehicles (CAVs), this paper proposes a Monte Carlo tree search (MCTS) method with parallel update for…

Large language models (LLMs) are becoming increasingly applied beyond natural language processing, demonstrating strong capabilities in complex scientific tasks that traditionally require human expertise. This progress has extended into…

In recent years, large language models (LLMs) have demonstrated significant potential in complex reasoning tasks like mathematical problem-solving. However, existing research predominantly relies on reinforcement learning (RL) frameworks…

Retrieval-augmented generation (RAG) systems have advanced large language models (LLMs) in complex deep search scenarios requiring multi-step reasoning and iterative information retrieval. However, existing approaches face critical…

This paper introduces AnalyticsGPT, an intuitive and efficient large language model (LLM)-powered workflow for scientometric question answering. This underrepresented downstream task addresses the subcategory of meta-scientific questions…

In robotic task planning, symbolic planners using rule-based representations like PDDL are effective but struggle with long-sequential tasks in complicated environments due to exponentially increasing search space. Meanwhile, LLM-based…

We present a scalable tree search planning algorithm for large multi-agent sequential decision problems that require dynamic collaboration. Teams of agents need to coordinate decisions in many domains, but naive approaches fail due to the…

Inference-time search algorithms such as Monte-Carlo Tree Search (MCTS) may seem unnecessary when generating natural language text based on state-of-the-art reinforcement learning such as Proximal Policy Optimization (PPO). In this paper,…

Multi-trajectory inference for tool-use LLM agents - generating multiple reasoning attempts and selecting among them - benefits from transferring knowledge across attempts so that later ones avoid the pitfalls of earlier ones. Existing…

Large language models (LLMs) have shown impressive performance in general programming tasks. However, in Machine Learning Engineering (MLE) scenarios such as AutoML and Kaggle competitions, achieving high performance depends heavily on…