JevAgentHarness

JevAgentHarness's activity

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

Leozkl 

updated 3 datasets 13 days ago

JevAgentHarness/coding-agent-decisions

Viewer • Updated 13 days ago • 66.9k • 273

JevAgentHarness/AgentDecision-train

Viewer • Updated 13 days ago • 23.8k • 378

JevAgentHarness/AgentDecisionBench

Viewer • Updated 13 days ago • 383k • 437 • 1

Leozkl 

updated 3 models 13 days ago

JevAgentHarness/AgentDecision-0.8B

Text Classification • Updated 13 days ago • 67

JevAgentHarness/AgentDecision-4B-v1

Text Classification • Updated 13 days ago • 66 • 1

JevAgentHarness/AgentDecision-4B

Text Classification • Updated 13 days ago • 113 • 4

Leozkl 

submitted a paper to Daily Papers 13 days ago

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

Paper • 2610.21412 • Published 14 days ago • 25

Leozkl 

published 3 models 13 days ago

JevAgentHarness/AgentDecision-4B-v1

Text Classification • Updated 13 days ago • 66 • 1

JevAgentHarness/AgentDecision-4B

Text Classification • Updated 13 days ago • 113 • 4

JevAgentHarness/AgentDecision-0.8B

Text Classification • Updated 13 days ago • 67

Leozkl 

published 3 datasets 13 days ago

JevAgentHarness/coding-agent-decisions

Viewer • Updated 13 days ago • 66.9k • 273

JevAgentHarness/AgentDecision-train

Viewer • Updated 13 days ago • 23.8k • 378

JevAgentHarness/AgentDecisionBench

Viewer • Updated 13 days ago • 383k • 437 • 1

Leozkl 

submitted a paper to Daily Papers 28 days ago

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

Paper • 2609.40111 • Published 29 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