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

Formative feedback is central to effective learning, yet providing timely, individualised feedback at scale remains a persistent challenge. While recent work has explored the use of large language models (LLMs) to automate feedback, most…

Knowledge Tracing (KT) models students' evolving knowledge states to predict future performance, serving as a foundation for personalized education. While traditional deep learning models achieve high accuracy, they often lack…

As agents operate over long horizons, their memory stores grow continuously, making retrieval critical to accessing relevant information. Many agent queries require reasoning-intensive retrieval, where the connection between query and…

Large language models often display undesirable behaviors embedded in their internal representations, undermining fairness, inconsistency drift, amplification of harmful content, and the propagation of unwanted patterns during extended…

The organization of latent knowledge within large-scale models poses unique challenges when addressing overlapping representations and optimizing contextual accuracy. Conceptual redundancies embedded across layers often result in…

Recent developments in large language models have shown advantages in reallocating a notable share of computational resource from training time to inference time. However, the principles behind inference time scaling are not well…

Inference-time scaling techniques have shown promise in enhancing the reasoning capabilities of large language models (LLMs). While recent research has primarily focused on training-time optimization, our work highlights inference-time…

Using more test-time computation during language model inference, such as generating more intermediate thoughts or sampling multiple candidate answers, has proven effective in significantly improving model performance. This paper takes an…

Conveying complex objectives to reinforcement learning (RL) agents can often be difficult, involving meticulous design of reward functions that are sufficiently informative yet easy enough to provide. Human-in-the-loop RL methods allow…

Large language models (LLMs) have rapidly progressed into general-purpose agents capable of solving a broad spectrum of tasks. However, current models remain inefficient at reasoning: they apply fixed inference-time compute regardless of…

Verification-guided self-improvement has recently emerged as a promising approach to improving the accuracy of large language model (LLM) outputs. However, existing approaches face a trade-off between inference efficiency and accuracy:…

Scaling model size and training data has led to great advances in the performance of Large Language Models (LLMs). However, the diminishing returns of this approach necessitate alternative methods to improve model capabilities, particularly…

Recent advancements in explainable recommendation have greatly bolstered user experience by elucidating the decision-making rationale. However, the existing methods actually fail to provide effective feedback signals for potentially better…

Large Language Models (LLMs) are increasingly used for clinical decision support, where hallucinations and unsafe suggestions may pose direct risks to patient safety. These risks are hard to assess: subtle clinical errors are often missed…

Inference-time computation is a powerful paradigm to enhance the performance of large language models (LLMs), with Best-of-N sampling being a widely used technique. However, this method is computationally expensive, requiring both (1) an…

Reasoning models have gained significant attention due to their strong performance, particularly when enhanced with retrieval augmentation. However, these models often incur high computational costs, as both retrieval and reasoning tokens…

Large language models (LLMs), based on transformer architectures, have revolutionized numerous domains within artificial intelligence, science, and engineering due to their exceptional scalability and adaptability. However, the exponential…

We study user history modeling via Transformer encoders in deep learning recommendation models (DLRM). Such architectures can significantly improve recommendation quality, but usually incur high latency cost necessitating infrastructure…

Traditional retrieval methods rely on transforming user queries into vector representations and retrieving documents based on cosine similarity within an embedding space. While efficient and scalable, this approach often fails to handle…

We study the problem of optimizing Large Language Model (LLM) inference scheduling to minimize total latency. LLM inference is an online and multi-task service process and also heavily energy consuming by which a pre-trained LLM processes…