Endless Terminals: Scaling RL Environments for Terminal Agents
Paper
• 2601.16443 • Published
• 17
Reading
-
-
Linear representations in language models can change dramatically over a conversation
Paper • 2601.20834 • Published • 21 -
Scaling Embeddings Outperforms Scaling Experts in Language Models
Paper • 2601.21204 • Published • 100 -
Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability
Paper • 2601.18778 • Published • 40 -
DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agents
Paper • 2601.20975 • Published • 9 -
Retrieval-Infused Reasoning Sandbox: A Benchmark for Decoupling Retrieval and Reasoning Capabilities
Paper • 2601.21937 • Published • 19 -
Length-Unbiased Sequence Policy Optimization: Revealing and Controlling Response Length Variation in RLVR
Paper • 2602.05261 • Published • 49 -
EgoActor: Grounding Task Planning into Spatial-aware Egocentric Actions for Humanoid Robots via Visual-Language Models
Paper • 2602.04515 • Published • 38 -
F-GRPO: Don't Let Your Policy Learn the Obvious and Forget the Rare
Paper • 2602.06717 • Published • 71 -
OPUS: Towards Efficient and Principled Data Selection in Large Language Model Pre-training in Every Iteration
Paper • 2602.05400 • Published • 335 -
PhyCritic: Multimodal Critic Models for Physical AI
Paper • 2602.11124 • Published • 52 -
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Paper • 2602.12036 • Published • 98 -
Gaia2: Benchmarking LLM Agents on Dynamic and Asynchronous Environments
Paper • 2602.11964 • Published • 12 -
GEBench: Benchmarking Image Generation Models as GUI Environments
Paper • 2602.09007 • Published • 39 -
GLM-5: from Vibe Coding to Agentic Engineering
Paper • 2602.15763 • Published • 96 -
DeepImageSearch: Benchmarking Multimodal Agents for Context-Aware Image Retrieval in Visual Histories
Paper • 2602.10809 • Published • 52 -
Experiential Reinforcement Learning
Paper • 2602.13949 • Published • 67 -
REDSearcher: A Scalable and Cost-Efficient Framework for Long-Horizon Search Agents
Paper • 2602.14234 • Published • 26 -
ResearchGym: Evaluating Language Model Agents on Real-World AI Research
Paper • 2602.15112 • Published • 20 -
SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks
Paper • 2602.12670 • Published • 52 -
jina-embeddings-v5-text: Task-Targeted Embedding Distillation
Paper • 2602.15547 • Published • 23 -
Discovering Multiagent Learning Algorithms with Large Language Models
Paper • 2602.16928 • Published • 14 -
Towards a Science of AI Agent Reliability
Paper • 2602.16666 • Published • 13 -
Empty Shelves or Lost Keys? Recall Is the Bottleneck for Parametric Factuality
Paper • 2602.14080 • Published • 20 -
A Very Big Video Reasoning Suite
Paper • 2602.20159 • Published • 435 -
TOPReward: Token Probabilities as Hidden Zero-Shot Rewards for Robotics
Paper • 2602.19313 • Published • 23 -
Mobile-O: Unified Multimodal Understanding and Generation on Mobile Device
Paper • 2602.20161 • Published • 21 -
Decoding as Optimisation on the Probability Simplex: From Top-K to Top-P (Nucleus) to Best-of-K Samplers
Paper • 2602.18292 • Published • 10 -
Unified Latents (UL): How to train your latents
Paper • 2602.17270 • Published • 53 -
DODO: Discrete OCR Diffusion Models
Paper • 2602.16872 • Published • 8