Related papers: SWE-Search: Enhancing Software Agents with Monte C…
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…
Large language models (LLMs) demonstrate impressive language understanding and contextual learning abilities, making them suitable for natural language processing (NLP) tasks and complex mathematical reasoning. However, when applied to…
The ability of a robot to plan complex behaviors with real-time computation, rather than adhering to predesigned or offline-learned routines, alleviates the need for specialized algorithms or training for each problem instance. Monte Carlo…
Large language models (LLMs) have advanced rapidly from conversational problem solving to addressing real-world tasks involving tool use, such as software engineering (SWE). Recent LLM-powered toolkits, such as OpenAI Codex and Cursor, have…
Large language models (LLMs) have demonstrated their remarkable capacity across a variety of tasks. However, reasoning remains a challenge for LLMs. To improve LLMs' reasoning ability, process supervision has proven to be better than…
We introduce MCTS-RAG, a novel approach that enhances the reasoning capabilities of small language models on knowledge-intensive tasks by leveraging retrieval-augmented generation (RAG) to provide relevant context and Monte Carlo Tree…
Large language models (LLMs) exhibit strong performance on self-contained programming tasks. However, they still struggle with repository-level software engineering (SWE), which demands (1) deep codebase navigation with effective context…
In this paper, we examine how large language models (LLMs) solve multi-step problems under a language agent framework with three components: a generator, a discriminator, and a planning method. We investigate the practical utility of two…
This study explores how to enhance the reasoning capabilities of large language models (LLMs) in knowledge base question answering (KBQA) by leveraging Monte Carlo Tree Search (MCTS). Semantic parsing-based KBQA methods are particularly…
Conversational Recommender Systems (CRS) proactively engage users in interactive dialogues to elicit user preferences and provide personalized recommendations. Existing methods train Reinforcement Learning (RL)-based agent with greedy…
Autonomous agents powered by language models (LMs) have demonstrated promise in their ability to perform decision-making tasks such as web automation. However, a key limitation remains: LMs, primarily optimized for natural language…
In response to the lack of trust in Artificial Intelligence (AI) for sequential planning, we design a Computational Tree Logic-guided large language model (LLM)-based natural language explanation framework designed for the Monte Carlo Tree…
Probabilistic search algorithms, such as Monte Carlo Tree Search (MCTS), have proven very effective in solving sequential decision-making tasks under uncertainty. However, interpreting asymmetric search trees that incorporate bandit-based…
Designing efficient reward functions for low-level control tasks is a challenging problem. Recent research aims to reduce reliance on expert experience by using Large Language Models (LLMs) with task information to generate dense reward…
Large Language Models (LLMs) are reshaping almost all industries, including software engineering. In recent years, a number of LLM agents have been proposed to solve real-world software problems. Such software agents are typically equipped…
The integration of autonomous vehicles into urban and highway environments necessitates the development of robust and adaptable behavior planning systems. This study presents an innovative approach to address this challenge by utilizing a…
Reinforcement learning (RL) has demonstrated notable success in post-training large language models (LLMs) as agents for tasks such as computer use, tool calling, and coding. However, exploration remains a central challenge in RL for LLM…
Accurate time series forecasting underpins decision-making across domains, yet conventional ML development suffers from data scarcity in new deployments, poor adaptability under distribution shift, and diminishing returns from manual…
LLM-based agents have shown promising capabilities in a growing range of software engineering (SWE) tasks. However, advancing this field faces two critical challenges. First, high-quality training data is scarce, especially data that…
Large Language Models (LLMs) demonstrate impressive capabilities, yet their outputs often suffer from misalignment with human preferences due to the inadequacy of weak supervision and a lack of fine-grained control. Training-time alignment…