arXiv
How to Train a Critic Stably and Efficiently
Group-based reinforcement learning methods such as GRPO for large language models avoid training a critic by sampling...
🤖 AI 前沿资讯
每天自动聚合 AI 领域最新动态
HuggingFace
Beyond Imitation: Filtering On-Policy Distillation by Reasoning Progress
On-policy distillation (OPD) has emerged as an effective framework for post-training language models by pairing stude...
HuggingFace
Prime Agent: A Self-Improving RLM Harness
Language models are sequential processors, but long-horizon agency requires external information and computation beyo...
HuggingFace
ReWorld: An Interactive World Model with Long-Horizon Memory
An interactive world model must follow the user's actions, remember the places it has shown, and stream in real time....
HuggingFace
Unlocking the Potential of Image Editing via Concept Scaling and Dense Supervision
Existing image editing frameworks predominantly follow the training paradigm of text-to-image diffusion models. Howev...
HuggingFace
GameXpert-Bench: How Far Are Coding Agents from Expert Game Development?
Recent large language models (LLMs) can operate as coding agents that build complete games from natural language requ...
HuggingFace
ARC: Fair Relative Advantage Comparison in Open-Ended Real-World Interaction
Open-ended real-world interaction admits multiple valid behaviors: an agent may answer directly, ask for clarificatio...
HuggingFace
Task-CoEvolve: Efficient Harness Optimization via Adaptive Validation Task Selection
We present a novel approach to efficient LLM harness optimization through adaptive validation task selection. Harness...
HuggingFace
Better Retrieval, Worse Robustness:How Multi-hop RAG Amplifies Upstream ASR Errors
Speech-based applications pass spoken queries through automatic speech recognition (ASR) before any retrieval module,...
HuggingFace
MobilePA-Bench: Benchmarking Mobile Planner Agents on Complex Real-World Tasks
As on-device LLM agents evolve into personal copilots, the mobile operating system has become a key testbed for this ...
HuggingFace
Block3D: Efficient Text-to-3D Generation via Block-Wise Diffusion
While text-to-3D generation has advanced rapidly, achieving high geometric fidelity at low inference cost remains cha...
HuggingFace
One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders
Search-augmented LLMs increasingly mediate everyday consumer recommendations by retrieving live web content. This cre...