Related papers: ScoreFlow: Mastering LLM Agent Workflows via Score…

In abstractive summarization, the challenge of producing concise and accurate summaries arises from the vast amount of information contained in the source document. Consequently, although Large Language Models (LLMs) can generate fluent…

We introduce Direct Value Optimization (DVO), an innovative reinforcement learning framework for enhancing large language models in complex reasoning tasks. Unlike traditional methods relying on preference labels, DVO utilizes value signals…

Fine-tuning pre-trained Large Language Models (LLMs) is essential to align them with human values and intentions. This process often utilizes methods like pairwise comparisons and KL divergence against a reference LLM, focusing on the…

Diffusion models have achieved impressive results in generative tasks such as text-to-image synthesis, yet they often struggle to fully align outputs with nuanced user intent and maintain consistent aesthetic quality. Existing…

Direct Preference Optimization (DPO) has gained significant attention for its simplicity and computational efficiency in aligning large language models (LLMs). Recent advancements have extended DPO to multimodal scenarios, achieving strong…

Recent advancements in reinforcement learning (RL) demonstrate the significant potential in autonomous driving. Despite this promise, challenges such as the manual design of reward functions and low sample efficiency in complex environments…

The performance of large language models (LLMs) depends on how they are prompted, with choices spanning both the high-level prompting pattern (e.g., Zero-Shot, CoT, ReAct, ReWOO) and the specific prompt content (instructions and few-shot…

Large language models (LLMs), despite their extensive pretraining on diverse datasets, require effective alignment to human preferences for practical and reliable deployment. Conventional alignment methods typically employ off-policy…

In the age of large language models (LLMs), autonomous agents have emerged as a powerful paradigm for achieving general intelligence. These agents dynamically leverage tools, memory, and reasoning capabilities to accomplish user-defined…

Agentic workflows in large language model systems integrate retrieval, reasoning, and memory, but existing frameworks suffer from scalability and reproducibility limitations due to fragmented data orchestration, serialization overhead, and…

Task-oriented dialogue systems based on Large Language Models (LLMs) have gained increasing attention across various industries and achieved significant results. Current approaches condense complex procedural workflows into a single agent…

Agentic workflows, where multiple AI agents collaborate to accomplish complex tasks like reasoning or planning, play a substantial role in many cutting-edge commercial applications, and continue to fascinate researchers across fields for…

While large-scale unsupervised language models (LMs) learn broad world knowledge and some reasoning skills, achieving precise control of their behavior is difficult due to the completely unsupervised nature of their training. Existing…

It is a notable trend to use Large Language Models (LLMs) to tackle complex tasks, e.g., tasks that require a sequence of actions and dynamic interaction with tools and external environments. In this paper, we propose StateFlow, a novel…

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.…

Large Language Models (LLMs) have shown impressive performance as general purpose agents, but their abilities remain highly dependent on prompts which are hand written with onerous trial-and-error effort. We propose a simple and…

Automatic Prompt Optimization (APO) has emerged as a critical technique for enhancing Large Language Model (LLM) performance, yet current state-of-the-art methods typically rely on large, labeled gold-standard development sets to compute…

Real-world trip planning requires transforming open-ended user requests into executable itineraries under strict spatial, temporal, and budgetary constraints while aligning with user preferences. Existing LLM-based agents struggle with…

The last year has witnessed the rapid progress of large language models (LLMs) across diverse domains. Among them, CodeLLMs have garnered particular attention because they can not only assist in completing various programming tasks but also…

Improving the alignment of language models with human preferences remains an active research challenge. Previous approaches have primarily utilized Reinforcement Learning from Human Feedback (RLHF) via online RL methods such as Proximal…