RESEARCH

Research

173 paper takes since 2026-08-19

RESEARCHVibeWorlding: Can Multimodal Agents Construct 3D Open Worlds End-to-End? · arXiv · Aug 19

Collision-free spatial editing is the unsolved core of 3D world construction, and RL post-training only partially closes it.

RL training lets open-source multimodal agents plan and build 3D scenes end-to-end, outperforming closed-source frontier models on this benchmark.

Read by the desk

↑52hf upvotes

RESEARCHUI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations · arXiv · Aug 19

A closed-loop data engine plus subtask-level demonstration learning closes most of the gap between open-weight GUI agents and frontier proprietary systems.

A foundation GUI agent that combines environment-grounded training with in-context demonstration learning to improve reliability on long-horizon office tasks.

Read by the desk

↑38hf upvotes

RESEARCHClawGym II: Exploring Black-Box RL on Agent Harness · arXiv · Aug 19

A concrete RL infrastructure for training through opaque production harnesses, with prefix-tree trajectory recovery and mix-harness training that actually holds up across 200–400 steps.

A black-box RL framework for optimizing agents through complex harnesses via sandbox execution, trajectory reconstruction, and mix-harness training.

Read by the desk

↑35hf upvotes

RESEARCHAn Empirical Study of Training Pixel-Space Text-to-Image Diffusion Models · arXiv · Aug 19

A disciplined ablation study that turns pixel-space diffusion from a slow-converging curiosity into a practical, faster-inference alternative to latent-space models.

Latent-to-pixel transfer training cuts convergence time and inference cost for large-scale pixel-space diffusion models.

Read by the desk

↑26hf upvotes

RESEARCHAgentic Transaction: Towards ACID-Compliant Agent Systems · arXiv · Aug 19

Treating failed-step isolation as a first-class design constraint, not an afterthought, accounts for most of the benchmark gain here.

A framework that brings ACID-style semantic guarantees to long-horizon LLM agent workflows.

Read by the desk

↑25hf upvotes