Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
• 23
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
ParetoSaddler: Pareto-Guided Optimization of Agent Harnesses for Quality and Cost
ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning
Articles
JueZhang
submitted a
paper to Daily Papers 4 minutes ago
Replace with v2 weights
#7 opened 1 day ago
by 
jakesmith-microsoft
Upload 2 files
#6 opened 1 day ago
by jakesmith-microsoft
tosch22
published a
model 4 days ago
abanerjeeml
updated a
dataset 4 days ago
xiaoyizhang-microsoft
updated a
model 5 days ago
xiaoyizhang-microsoft
published a
model 5 days ago
Convert policy.json to the Rho format and remove RhoAlpha tensor aliases
#1 opened 11 days ago
by 
akolobov
Convert policy.json to the Rho format and remove RhoAlpha tensor aliases
#1 opened 11 days ago
by akolobov
abanerjeeml
published a
dataset 7 days ago
lx865712528
authored 3
papers 8 days ago
SOAR: Source-Aware Reinforcement Learning with Precise Credit Assignment for Search Agents
Paper • 2610.13157 • Published
Expert-Space Exploration in MoE Reinforcement Learning
Paper • 2609.13058 • Published • 9
AgentRL: Scaling Agentic Reinforcement Learning with a Multi-Turn, Multi-Task Framework
Paper • 2510.04206 • Published • 3
AnuarSh
updated a
model 8 days ago
v-xchen-v
published a
model 9 days ago
v-xchen-v
updated a
model 10 days ago
Convert policy.json to the Rho format and remove RhoAlpha tensor aliases
#1 opened 11 days ago
by akolobov
Convert policy.json to the Rho format and remove RhoAlpha tensor aliases
#1 opened 11 days ago
by akolobov
Add raw .kicad_sch schematics
#2 opened 12 days ago
by 
ruichunma
Article
Turning Database Grading into RL Rewards: Post-Training Agents with ThinkingBox
microsoft
• • 23