JevAgentHarness

JevAgentHarness's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

Leozkl 

updated 3 datasets 1 day ago

JevAgentHarness/coding-agent-decisions

Viewer • Updated 1 day ago • 66.9k • 78

JevAgentHarness/AgentDecision-train

Viewer • Updated 1 day ago • 23.8k • 100

JevAgentHarness/AgentDecisionBench

Viewer • Updated 1 day ago • 383k • 102 • 1

Leozkl 

updated 3 models 1 day ago

JevAgentHarness/AgentDecision-0.8B

Text Classification • Updated 1 day ago • 26

JevAgentHarness/AgentDecision-4B-v1

Text Classification • Updated 1 day ago • 23

JevAgentHarness/AgentDecision-4B

Text Classification • Updated 1 day ago • 26

Leozkl 

submitted a paper to Daily Papers 1 day ago

JevAgentHarness: Benchmarking, Deploying and Training Decision Models That Share Control with LLMs

Paper • 2610.21412 • Published 3 days ago • 18

Leozkl 

published 3 models 2 days ago

JevAgentHarness/AgentDecision-4B-v1

Text Classification • Updated 1 day ago • 23

JevAgentHarness/AgentDecision-4B

Text Classification • Updated 1 day ago • 26

JevAgentHarness/AgentDecision-0.8B

Text Classification • Updated 1 day ago • 26

Leozkl 

published 3 datasets 2 days ago

JevAgentHarness/coding-agent-decisions

Viewer • Updated 1 day ago • 66.9k • 78

JevAgentHarness/AgentDecision-train

Viewer • Updated 1 day ago • 23.8k • 100

JevAgentHarness/AgentDecisionBench

Viewer • Updated 1 day ago • 383k • 102 • 1

Leozkl 

submitted a paper to Daily Papers 16 days ago

Agent Error Dataset: Scaling 50,000 Error--Diagnosis Pairs for Failure Analysis and Error-Aware Post-Training

Paper • 2609.40111 • Published 18 days ago • 52

Leozkl 

submitted a paper to Daily Papers 3 months ago

AgentDebugX: An Open-Source Toolkit for Failure Observability, Attribution, and Recovery in LLM Agents

Paper • 2607.18754 • Published Jul 21 • 25