…View arXiv page View PDF Add to collection Community This paper proposes a method to predict data diversity, difficulty, and quality with SAE signals, which guides LLM RL post-training data engineering…
…View arXiv page View PDF Project page Add to collection Community Modern generative models possess a deep understanding of visual content, yet training them for image editing typically requires massive datasets of…
…View arXiv page View PDF Project page Add to collection Community FINAL Bench introduces a new evaluation paradigm for LLMs: functional metacognitive reasoning — not just "can the model solve it," but "does…
…View arXiv page View PDF GitHub 4 Add to collection Community ICML 2026 Made an audio walkthrough of this paper for anyone who wants to skim it on the go: https://researchpod…
…To determine which memories should be reused and retained, SkeMex estimates context-dependent utility from environment feedback and uses it to guide value-aware retrieval and repository governance . A closed-loop `` Read…
…Furthermore, effective procedural 3D modeling requires a robust execution environment that provides high-fidelity feedback for iterative refinement . We release 3DCodeBench, including the curated large-scale dataset of multimodal (text/image) prompts…
…View arXiv page View PDF Project page Add to collection Community SOTA, open-source small coding-focused model! This is an automated message from the Librarian Bot . I found the following papers…
…View arXiv page View PDF Add to collection Community This paper presents UniSteer, a text-guided flow matching framework for steering LLM activations. The goal is to provide a unified interface where…
…View arXiv page View PDF Add to collection Community Standard RL rewards LLM agents for good actions, but ignores what those actions change. Our proposed PaW turns every RL rollout into world…
…However, they still struggle to learn complex long-term curation policies from indirect and delayed feedback. To tackle this challenge, we propose SkillOS, an experience-driven RL training recipe for learning skill…