Microsoft Research

company

https://www.microsoft.com/en-us/research/

AI & ML interests

None defined yet.

Recent Activity

ChilleD submitted a paper 2 days ago

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

weizhepei submitted a paper 4 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

aaronjli submitted a paper 4 days ago

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

View all activity

Papers

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Self-Evolving Coding Agents via Harness-Policy Optimization

View all Papers

submitted a paper to Daily Papers 2 days ago

Agent World Model in the Wild: Computer-Use Agent Environment Synthesis

Paper • 2610.26828 • Published 6 days ago • 84

submitted a paper to Daily Papers 4 days ago

Self-Evolving Coding Agents via Harness-Policy Optimization

Paper • 2610.22791 • Published 9 days ago • 56

submitted a paper to Daily Papers 4 days ago

TokenEconomizer: Experience-Driven Black-Box Cost Control for Coding Agents

Paper • 2610.22732 • Published 10 days ago • 5

submitted a paper to Daily Papers 9 days ago

APT: Feedback-Driven Agentic Post-Training for Text-to-Image Generation

Paper • 2610.18097 • Published 11 days ago • 31

submitted a paper to Daily Papers 17 days ago

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

Paper • 2610.04933 • Published 21 days ago • 17

submitted a paper to Daily Papers 19 days ago

CUAWright: A Minimal Unified Interface for Digital Agents

Paper • 2610.04116 • Published 23 days ago • 6

submitted a paper to Daily Papers 25 days ago

Reinforcing Agentic Creativity in Scientific Ideation with Night Science

Paper • 2609.35706 • Published 27 days ago • 5

submitted a paper to Daily Papers about 1 month ago

Agensh: Scaling Organizational Intelligence to 1,024 Agents

Paper • 2609.26781 • Published Sep 22 • 29

submitted a paper to Daily Papers about 1 month ago

ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models

Paper • 2609.13231 • Published Sep 2 • 19

submitted a paper to Daily Papers about 1 month ago

BI-Agent and BI-Bench: Towards Automating End-to-End Business Intelligence

Paper • 2609.20886 • Published Sep 16 • 30

submitted a paper to Daily Papers about 1 month ago

ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks

Paper • 2609.18805 • Published Sep 16 • 67

Lin0

submitted a paper to Daily Papers about 1 month ago

Expert-Space Exploration in MoE Reinforcement Learning

Paper • 2609.13058 • Published Sep 11 • 9

submitted a paper to Daily Papers about 2 months ago

StudentSim: Training LLM-based Student Simulators

Paper • 2609.01591 • Published Sep 1 • 535

submitted a paper to Daily Papers 2 months ago

Dion3: Full-Stack Orthogonal Updates

Paper • 2608.11612 • Published Aug 12 • 11

submitted a paper to Daily Papers 2 months ago

Full-bandwidth transformer

Paper • 2608.08888 • Published Aug 9 • 25

submitted a paper to Daily Papers 3 months ago

Weak-to-Strong On-Policy Distillation

Paper • 2607.26246 • Published Jul 28 • 59

submitted a paper to Daily Papers 3 months ago

Echoverse: Deep, Evolving Environments for Training Computer-Use Agents at Scale

Paper • 2607.28074 • Published Jul 30 • 13

submitted a paper to Daily Papers 3 months ago

Multi-Turn On-Policy Distillation with Prefix Replay

Paper • 2607.04763 • Published Jul 16 • 13

submitted a paper to Daily Papers 3 months ago

LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks

Paper • 2607.18110 • Published Jul 20 • 17

submitted a paper to Daily Papers 4 months ago

Object-Centric Residual RL for Zero-Shot Sim-to-Real VLA Enhancement

Paper • 2606.18953 • Published Jun 17 • 8