Do LLMs Benefit From Their Own Words?
arXiv:2602.24287v1 Announce Type: cross Abstract: Multi-turn interactions with large language models typically retain the assistant’s own past responses in the…
MoDora: Tree-Based Semi-Structured Document Analysis System
arXiv:2602.23061v2 Announce Type: replace-cross Abstract: Semi-structured documents integrate diverse interleaved data elements (e.g., tables, charts, hierarchical paragraphs) arranged in various…
Graph Your Way to Inspiration: Integrating Co-Author Graphs with Retrieval-Augmented Generation for Large Language Model Based Scientific Idea Generation
arXiv:2602.22215v1 Announce Type: new Abstract: Large Language Models (LLMs) demonstrate potential in the field of scientific idea generation. However, the…
Hierarchical LLM-Based Multi-Agent Framework with Prompt Optimization for Multi-Robot Task Planning
arXiv:2602.21670v2 Announce Type: replace-cross Abstract: Multi-robot task planning requires decomposing natural-language instructions into executable actions for heterogeneous robot teams. Conventional…
dLLM: Simple Diffusion Language Modeling
arXiv:2602.22661v1 Announce Type: cross Abstract: Although diffusion language models (DLMs) are evolving quickly, many recent models converge on a set…
Instruction-based Image Editing with Planning, Reasoning, and Generation
arXiv:2602.22624v1 Announce Type: cross Abstract: Editing images via instruction provides a natural way to generate interactive content, but it is…
Why Pass@k Optimization Can Degrade Pass@1: Prompt Interference in LLM Post-training
arXiv:2602.21189v2 Announce Type: replace-cross Abstract: Pass@k is a widely used performance metric for verifiable large language model tasks, including mathematical…
A family of large language models for materials research with insights into model adaptability in continued pretraining
Nature Machine Intelligence, Published online: 27 February 2026; doi:10.1038/s42256-026-01199-8 Dhruv et al. introduce LLaMat, a family of LLMs for materials…
A universal spin–orbit-coupled Hamiltonian model for accelerated quantum material discovery
Nature Machine Intelligence, Published online: 27 February 2026; doi:10.1038/s42256-026-01196-x Zhong et al. introduce Uni-HamGNN, a graph neural network model that…