Related papers: Memory-Guided Tree Search with Cross-Branch Knowle…

Combinatorial optimization (CO) layers in machine learning (ML) pipelines are a powerful tool to tackle data-driven decision tasks, but they come with two main challenges. First, the solution of a CO problem often behaves as a piecewise…

Multi-intent natural language understanding requires retrieval systems that simultaneously achieve high accuracy and computational efficiency, yet existing approaches apply either uniform single-step retrieval that compromises recall or…

To enable embodied agents to operate effectively over extended timeframes, it is crucial to develop models that form and access memories to stay contextualized in their environment. In the current paradigm of training transformer-based…

Recent methodologies in LLM self-training mostly rely on LLM generating responses and filtering those with correct output answers as training data. This approach often yields a low-quality fine-tuning training set (e.g., incorrect plans or…

Modern pre-trained architectures struggle to retain previous information while undergoing continuous fine-tuning on new tasks. Despite notable progress in continual classification, systems designed for complex vision tasks such as detection…

We present a study of several generic tree search techniques applied to the Sequential Ordering Problem. This study enables us to propose a simple and competitive tree search algorithm. It consists of an iterative Beam Search algorithm that…

Memory is a fundamental component for enabling long-context LLM agents, supporting persistent state across interactions through a continuous serve-and-update lifecycle. Despite substantial prior work, existing systems suffer from…

Recent advances in large language models (LLMs) have unlocked powerful reasoning and decision-making capabilities. However, their inherent dependence on static parametric memory fundamentally limits their adaptability, factual accuracy, and…

Large Language Models (LLMs) have demonstrated remarkable potential in handling complex reasoning tasks by generating step-by-step rationales.Some methods have proven effective in boosting accuracy by introducing extra verifiers to assess…

Contemporary progress in large language models (LLMs) has revealed notable inferential capacities via reinforcement learning (RL) employing verifiable reward, facilitating the development of O1 and R1-like reasoning models. Directly…

Existing memory systems enable Large Language Models (LLMs) to support long-horizon human-LLM interactions by persisting historical interactions beyond limited context windows. However, while recent approaches have succeeded in constructing…

Inference-time scaling strategies, particularly Monte Carlo Tree Search (MCTS), have significantly enhanced the reasoning capabilities of Large Language Models (LLMs). However, current approaches remain predominantly stateless, discarding…

The ability to reason is one of the most fundamental capabilities of large language models (LLMs), enabling a wide range of downstream tasks through sophisticated problem-solving. A critical aspect of this is code reasoning, which involves…

Large Language Models (LLMs) excel at general code generation, but their performance drops sharply in enterprise settings that rely on internal private libraries absent from public pre-training corpora. While Retrieval-Augmented Generation…

Decision tree learning is a widely used approach in machine learning, favoured in applications that require concise and interpretable models. Heuristic methods are traditionally used to quickly produce models with reasonably high accuracy.…

The advancement of Large Language Models (LLMs) has brought substantial attention to the Chain of Thought (CoT) approach, primarily due to its ability to enhance the capability of LLMs on complex reasoning tasks. Moreover, the significance…

Retrieval-augmented generation (RAG) integrates large language models ( LLM s) with retrievers to access external knowledge, improving the factuality of LLM generation in knowledge-grounded tasks. To optimize the RAG performance, most…

LLMs have demonstrated strong mathematical reasoning abilities by leveraging reinforcement learning with long chain-of-thought, yet they continue to struggle with theorem proving due to the lack of clear supervision signals when solely…

Despite the substantial success of Information Retrieval (IR) in various NLP tasks, most IR systems predominantly handle queries and corpora in natural language, neglecting the domain of code retrieval. Code retrieval is critically…

Memory data are ubiquitous in Large Language Model (LLM)-based agents (e.g., OpenClaw and Manus). A few recent works have attempted to exploit agents'memory for improving their performance on the question-answering (QA) task, but they lack…