Related papers: UPA: Unsupervised Prompt Agent via Tree-Based Sear…

Reinforcement Learning (RL) traditionally relies on scalar reward signals, limiting its ability to leverage the rich semantic knowledge often available in real-world tasks. In contrast, humans learn efficiently by combining numerical…

Large Language Model (LLM) training often optimizes for preference alignment, rewarding outputs that are perceived as helpful and interaction-friendly. However, this preference-oriented objective can be exploited: manipulative prompts can…

Large language model (LLM)-based search agents have proven promising for addressing knowledge-intensive problems by incorporating information retrieval capabilities. Existing works largely focus on optimizing the reasoning paradigms of…

Large Language Models (LLMs) have demonstrated remarkable progress in instruction following and general-purpose reasoning. However, achieving high-quality alignment with human intent and safety norms without human annotations remains a…

Assessing risk of bias (RoB) in randomized controlled trials is essential for trustworthy evidence synthesis, but the process is resource-intensive and prone to variability across reviewers. Large language models (LLMs) offer a route to…

The goal of unbiased learning to rank (ULTR) is to leverage implicit user feedback for optimizing learning-to-rank systems. Among existing solutions, automatic ULTR algorithms that jointly learn user bias models (i.e., propensity models)…

Enabling large language models (LLMs) to utilize search tools offers a promising path to overcoming fundamental limitations such as knowledge cutoffs and hallucinations. Recent work has explored reinforcement learning (RL) for training…

Large language models achieve state-of-the-art performance but are increasingly costly to fine-tune. Prompt tuning is a parameter-efficient fine-tuning method that addresses parameter-efficiency by learning prompt embeddings, but these…

The potential of reinforcement learning (RL) to deliver aligned and performant agents is partially bottlenecked by the reward engineering problem. One alternative to heuristic trial-and-error is preference-based RL (PbRL), where a reward…

Large Language Models (LLMs) have shown remarkable capabilities in natural language tasks requiring complex reasoning, yet their application in agentic, multi-step reasoning within interactive environments remains a difficult challenge.…

Owing to recent advancements, Large Language Models (LLMs) can now be deployed as agents for increasingly complex decision-making applications in areas including robotics, gaming, and API integration. However, reflecting past experiences in…

While Pre-trained Language Models (PLMs) internalize a great amount of world knowledge, they have been shown incapable of recalling these knowledge to solve tasks requiring complex & multi-step reasoning. Similar to how humans develop a…

Prompt engineering is a crucial yet challenging task for optimizing the performance of large language models (LLMs) on customized tasks. This pioneering research introduces the Automatic Prompt Engineering Toolbox (APET), which enables…

Recent work explores agentic inference-time techniques to perform structured, multi-step reasoning. However, stateless inference often struggles on multi-step tasks due to the absence of persistent state. Moreover, task-specific fine-tuning…

A Persuasive Teachable Agent (PTA) is a special type of Teachable Agent which incorporates a persuasion theory in order to provide persuasive and more personalized feedback to the student. By employing the persuasion techniques, the PTA…

Consider a principal who wants to search through a space of stochastic solutions for one maximizing their utility. If the principal cannot conduct this search on their own, they may instead delegate this problem to an agent with distinct…

Search agents powered by large language models can autonomously decompose queries, retrieve information, and synthesize answers through multi-step reasoning. However, the rapid growth of training methods has outpaced controlled comparison:…

Aligning language models to human expectations, e.g., being helpful and harmless, has become a pressing challenge for large language models. A typical alignment procedure consists of supervised fine-tuning and preference learning. Most…

Retrieval-Augmented Generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, yet traditional single-round retrieval struggles with complex multi-step reasoning. Agentic RAG addresses this by enabling LLMs…

Large language models (LLMs) have revolutionized natural language processing by solving a wide range of tasks simply guided by a prompt. Yet their performance is highly sensitive to prompt formulation. While automatic prompt optimization…