Anonymous double-blind workshop supplement: training traces, eval data and LoRA adapters for a per-turn-cap agent study.
hfunknown
hfunknown
AI & ML interests
None yet
Recent Activity
updated a dataset about 11 hours ago
hfunknown/cap-sweep-training-traces updated a dataset about 11 hours ago
hfunknown/cap-sweep-eval-data updated a collection 5 days ago
Runtime Persistence Agent Evaluation (Anonymous)Organizations
None yet
models 14
hfunknown/qwen3-8b-navigation-lora-stateless
Text Generation • Updated • 30
hfunknown/qwen3-8b-navigation-lora-persistent
Text Generation • Updated • 33
hfunknown/qwen3-8b-rule_diagnosis-lora-stateless
Text Generation • Updated • 33
hfunknown/qwen3-8b-rule_diagnosis-lora-persistent
Text Generation • Updated • 37
hfunknown/llama31-8b-knapsack-lora-stateless
Text Generation • Updated • 254
hfunknown/llama31-8b-knapsack-lora-persistent
Text Generation • Updated • 43
hfunknown/mistral-7b-knapsack-lora-stateless
Text Generation • Updated • 22
hfunknown/mistral-7b-knapsack-lora-persistent
Text Generation • Updated • 25
hfunknown/qwen3-8b-knapsack-lora-stateless-seed1337
Text Generation • Updated • 7
hfunknown/qwen3-8b-knapsack-lora-persistent-seed1337
Text Generation • Updated • 7