We introduce SELF-DISCOVER, a general framework for LLMs to self-discover the task-
intrinsic reasoning structures to tackle complex reasoning problems that are challenging for …

Large language models (LLMs) have shown great potential in complex reasoning tasks, yet
their performance is often hampered by the scarcity of high-quality and reasoning-focused …

Decision-making is a fundamental capability in everyday life. Large Language Models
(LLMs) provide multifaceted support in enhancing human decision-making processes …

This survey summarises the most recent methods for building and assessing helpful, honest,
and harmless neural language models, considering small, medium, and large-size models …

The current paradigm of evaluating Large Language Models (LLMs) through static
benchmarks comes with significant limitations, such as vulnerability to data contamination …

Large language models (LLMs) have achieved remarkable performance in various
evaluation benchmarks. However, concerns are raised about potential data contamination in …

Planning is a fundamental property of human intelligence. Reasoning about asynchronous
plans is challenging since it requires sequential and parallel planning to optimize time costs …

Language model agents (LMA) recently emerged as a promising paradigm on muti-step
decision making tasks, often outperforming humans and other reinforcement learning …

While vision-language models (VLMs) have demonstrated remarkable performance across
various tasks combining textual and visual information, they continue to struggle with fine …

Reasoning is most powerful when an LLM accurately aggregates relevant information. We
examine the critical role of information aggregation in reasoning by requiring the LLM to …