Related papers: Distilling Feedback into Memory-as-a-Tool

We examine the reasoning and planning capabilities of large language models (LLMs) in solving complex tasks. Recent advances in inference-time techniques demonstrate the potential to enhance LLM reasoning without additional training by…

Recent studies provide large language models (LLMs) with textual task-solving experiences via prompts to improve their performance. However, previous methods rely on substantial human labor or time to gather such experiences for each task,…

A common approach to personalization in large language models (LLMs) is to incorporate a subset of the user memory into the prompt at inference time to guide the model's generation. Existing methods select these subsets primarily using…

Large language models (LLMs) achieved remarkable performance across various tasks. However, they face challenges in managing long documents and extended conversations, due to significantly increased computational requirements, both in…

The trade-off between labeled data availability and downstream accuracy remains a central challenge in fine-tuning large language models (LLMs). We propose a principled framework for \emph{budget-aware supervised fine-tuning} by casting LLM…

Large Language Models (LLMs) can enhance their reasoning capabilities by using external tools. However, many tasks lack predefined tools. Prior works have explored instructing LLMs to generate tools on their own, but such approaches depend…

Large Language Models (LLMs) have revolutionized recommendation agents by providing superior reasoning and flexible decision-making capabilities. However, existing methods mainly follow a passive information acquisition paradigm, where…

We propose RT (Refine Thought), a method that can enhance the semantic rea-soning ability of text embedding models. The method obtains the final semanticrepresentation by running multiple forward passes of the text embedding…

Recent advancements in large language models (LLMs) have catalyzed the development of general-purpose autonomous agents, demonstrating remarkable performance in complex reasoning tasks across various domains. This surge has spurred the…

Recommendation is the task of improving customer experience through personalized recommendation based on users' past feedback. In this paper, we investigate the most common scenario: the user-item (U-I) matrix of implicit feedback. Even…

Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search…

LLM-based agents have been extensively applied across various domains, where memory stands out as one of their most essential capabilities. Previous memory mechanisms of LLM-based agents are manually predefined by human experts, leading to…

Parameter-efficient methods are able to use a single frozen pre-trained large language model (LLM) to perform many tasks by learning task-specific soft prompts that modulate model behavior when concatenated to the input text. However, these…

The exploration of whether agents can align with their environment without relying on human-labeled data presents an intriguing research topic. Drawing inspiration from the alignment process observed in intelligent organisms, where…

Performing inference on large volumes of samples with large language models (LLMs) can be computationally and financially costly in industry and real-world use. We propose batch prompting, a simple yet effective prompting approach that…

We propose a scalable method for constructing a temporal opinion knowledge base with large language models (LLMs) as automated annotators. Despite the demonstrated utility of time-series opinion analysis of text for downstream applications…

While Experience Replay - the practice of storing rollouts and reusing them multiple times during training - is a foundational technique in general RL, it remains largely unexplored in LLM post-training due to the prevailing belief that…

With the rapid growth of Internet services, recommendation systems play a central role in delivering personalized content. Faced with massive user requests and complex model architectures, the key challenge for real-time recommendation…

The field of efficient Large Language Model (LLM) inference is rapidly evolving, presenting a unique blend of opportunities and challenges. Although the field has expanded and is vibrant, there hasn't been a concise framework that analyzes…

We envision a continuous collaborative learning system where groups of LLM agents work together to solve reasoning problems, drawing on memory they collectively build to improve performance as they gain experience. This work establishes the…