Self-discover: Large language models self-compose reasoning structures

P Zhou, J Pujara, X Ren, X Chen… - Advances in …, 2025 - proceedings.neurips.cc
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 …

Evaluating frontier models for dangerous capabilities

M Phuong, M Aitchison, E Catt, S Cogan… - arxiv preprint arxiv …, 2024 - arxiv.org
To understand the risks posed by a new AI system, we must understand what it can and
cannot do. Building on prior work, we introduce a programme of new" dangerous capability" …

A systematic survey on large language models for algorithm design

F Liu, Y Yao, P Guo, Z Yang, Z Zhao, X Lin… - arxiv preprint arxiv …, 2024 - arxiv.org
Algorithm Design (AD) is crucial for effective problem-solving across various domains. The
advent of Large Language Models (LLMs) has notably enhanced the automation and …

MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making

D Fu, B Qi, Y Gao, C Jiang, G Dong, B Zhou - arxiv preprint arxiv …, 2024 - arxiv.org
Long-term memory is significant for agents, in which insights play a crucial role. However,
the emergence of irrelevant insight and the lack of general insight can greatly undermine the …