Get Started
Home
Topics
Search
Library
273 papers · page 1 of 28

Research archive

Every paper covered by r*cap, newest first.
FDE-Gym: The Last Mile of AI Delivery
Agents · Added Oct 17 · 11:17
More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning
Agents · Added Oct 16 · 7:40
Beyond Domain-Routed Supervision: Cross-Teacher Guarding for Multi-Teacher On-Policy Distillation
LLM Training · Added Oct 16 · 6:12
Player-1: Learning to Play from Synthetic Experience
Agents · Added Oct 16 · 8:22
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Agents · Added Oct 16 · 9:20
Urbex: Agentic Spatial Grounding for City-Scale 3D Scenes
Agents · Added Oct 15 · 7:45
Agent-Reflex: Teaching Language Agents to Act Reflectively
Agents · Added Oct 15 · 8:25
AgentSWE: Can Coding Agents Build the Agent You Actually Want?
Agents · Added Oct 14 · 8:31
S-Space: Exploring Spatial Workspace in Multimodal Language Models
Mechanistic Interpretability · Added Oct 13 · 7:30
Reflex: Visually Grounded Reactive Humanoid Control
Reinforcement Learning · Added Oct 13 · 5:24
12345678910111213141516171819202122232425262728