相关论文: Hierarchical Pedagogical Oversight: A Multi-Agent …

Long-horizon decision-making tasks present significant challenges for LLM-based agents due to the need for extensive planning over multiple steps. In this paper, we propose a hierarchical framework that decomposes complex tasks into…

Reasoning, the process of devising and executing complex goal-oriented action sequences, remains a critical challenge in AI. Current large language models (LLMs) primarily employ Chain-of-Thought (CoT) techniques, which suffer from brittle…

Due to the high computational demands executing a rigorous comparison between hyperparameter optimization (HPO) methods is often cumbersome. The goal of this paper is to facilitate a better empirical evaluation of HPO methods by providing…

Learning anticipation is a reasoning paradigm in multi-agent reinforcement learning, where agents, during learning, consider the anticipated learning of other agents. There has been substantial research into the role of learning…

In recent years, Dialogue-style Large Language Models (LLMs) such as ChatGPT and GPT4 have demonstrated immense potential in constructing open-domain dialogue agents. However, aligning these agents with specific characters or individuals…

In recent years, reinforcement learning has achieved many remarkable successes due to the growing adoption of deep learning techniques and the rapid growth in computing power. Nevertheless, it is well-known that flat reinforcement learning…

Recently, latent reasoning has been introduced into large language models (LLMs) to leverage rich information within a continuous space. However, without stochastic sampling, these methods inevitably collapse to deterministic inference,…

The evaluation of large language models (LLMs) has predominantly relied on static datasets, which offer limited scalability and fail to capture the evolving reasoning capabilities of recent models. To overcome these limitations, we propose…

While Reinforcement Learning (RL) shows promise in training tool-use Large Language Models (LLMs) using verifiable outcome rewards, existing methods largely overlook the potential of reasoning rewards based on chain-of-thought quality for…

Large language models (LLMs) have become widely adopted as automated judges for evaluating AI-generated content. Despite their success, aligning LLM-based evaluations with human judgments remains challenging. While supervised fine-tuning on…

Alignment of large language models (LLMs) has predominantly relied on pairwise preference optimization, where annotators select the better of two responses to a prompt. While simple, this approach overlooks the opportunity to learn from…

Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reasons, and (3) how tasks are decomposed across components. Yet…

Hyperparameter Optimization (HPO) is crucial to develop well-performing machine learning models. In order to ease prototyping and benchmarking of HPO methods, we propose carps, a benchmark framework for Comprehensive Automated Research…

Reinforcement Learning from Human Feedback (RLHF) has emerged as a powerful technique for aligning large language models (LLMs) with human preferences. However, effectively aligning LLMs with diverse human preferences remains a significant…

Multi-agent systems of large language models (LLMs) show promise for complex reasoning, but their effectiveness is often limited by fixed collaboration protocols. These frameworks typically focus on macro-level orchestration while…

Large Language Models (LLMs) have demonstrated remarkable capabilities through pretraining and alignment. However, superior short-context LLMs may underperform in long-context scenarios due to insufficient long-context alignment. This…

Large Language Models (LLMs) can struggle to balance gullibility to misinformation and resistance to valid corrections in persuasive dialogues, a critical challenge for reliable deployment. We introduce DuET-PD (Dual Evaluation for Trust in…

The Group Relative Policy Optimization (GRPO) algorithm has demonstrated considerable success in enhancing the reasoning capabilities of large language models (LLMs), as evidenced by DeepSeek-R1. However, the absence of intermediate…

Educational NLP systems are typically evaluated using engagement metrics and satisfaction surveys, which are at best a proxy for meeting pedagogical goals. We introduce six computational metrics for automated evaluation of pedagogical…

Computer-aided teacher training is a state-of-the-art method designed to enhance teachers' professional skills effectively while minimising concerns related to costs, time constraints, and geographical limitations. We investigate the…