…View arXiv page View PDF Project page GitHub 132 Add to collection Community Can an AI agent act like an editor, turning raw data into readable, verifiable, multimodal stories? Data2Story brings data…
…View arXiv page View PDF GitHub 3 Add to collection Community 🤔 When does training a multi-agent LLM workflow end-to-end with RL actually help, and when does it quietly…
…Code (https://github.com/hrtan/fastmix) View arXiv page View PDF GitHub 3 Add to collection Community Excited to share our team's (Tencent Hunyuan, HKU, CUHK) work from last year: "Fast…
…View arXiv page View PDF Project page GitHub 6 Add to collection Community We introduce an axiomatic evaluation framework for latent thought representations in LLMs, comprising metrics that are independent of downstream…
…do not train a network to discover an entire algorithm blindly. Instead (1) expose the latent algebra in the representation (phase encoding), (2) break the symmetry (real weights), (3) train the network…
…View arXiv page View PDF Project page GitHub 29 Add to collection Community 💡 Deeper is Not Always Better: Bypassing the "Alignment Tax" in LLMs Standard practice assumes that the deeper a layer…
…View arXiv page View PDF GitHub 43 Add to collection Community Traditional indexing for large language model personalization and search can be rigid and resource-intensive. In this paper, we explore a…
…View arXiv page View PDF Project page GitHub 38 Add to collection Community General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.