-
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Paper • 2606.26300 • Published • 54 -
Autodata: An agentic data scientist to create high quality synthetic data
Paper • 2606.25996 • Published • 21 -
OpenThoughts-Agent: Data Recipes for Agentic Models
Paper • 2606.24855 • Published • 49 -
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Paper • 2606.22883 • Published • 38
Tianjian Li
dogtooth
AI & ML interests
None yet
Recent Activity
upvoted a paper 3 days ago
Into the Unknown: Benchmarking AI agents on open scientific research problems upvoted a paper about 1 month ago
RecreationWorld: Scalable and Verifiable Environments for Hybrid Computer-Use Agents updated a collection 4 months ago
good-papersOrganizations
-
The Verification Horizon: No Silver Bullet for Coding Agent Rewards
Paper • 2606.26300 • Published • 54 -
Autodata: An agentic data scientist to create high quality synthetic data
Paper • 2606.25996 • Published • 21 -
OpenThoughts-Agent: Data Recipes for Agentic Models
Paper • 2606.24855 • Published • 49 -
CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents
Paper • 2606.22883 • Published • 38
models 38
dogtooth/open-lm-3b-201305-midtrain-stage2-think
Text Generation • 3B • Updated • 6
dogtooth/open-lm-3b-201305-midtrain
Text Generation • 3B • Updated • 14
dogtooth/open-lm-3b-201305-midtrain-stage1-sft
Text Generation • 3B • Updated • 13
dogtooth/open-lm-3b-202407-stage2-think
3B • Updated • 5
dogtooth/open-lm-3b-202101-stage2-think
3B • Updated • 2
dogtooth/open-lm-3b-201901-stage2-think
3B • Updated • 5
dogtooth/open-lm-3b-201701-stage2-think
3B • Updated • 8
dogtooth/open-lm-3b-201501-stage2-think
3B • Updated • 4
dogtooth/open-lm-3b-202301-stage2-think
3B • Updated • 3
dogtooth/open-lm-3b-201901-stage1-sft
Text Generation • 3B • Updated • 10
datasets 46
dogtooth/reasoning_state_rl
Viewer • Updated • 262k • 9
dogtooth/rc-annotated-sft
Viewer • Updated • 1.49k • 8
dogtooth/polaris_filtered_removed_all_correct
Viewer • Updated • 38.1k • 9
dogtooth/polaris_filtered_less_than_half_correct
Viewer • Updated • 13.8k • 4
dogtooth/llm_tool_self_context_management_sft
Viewer • Updated • 12.4k • 7
dogtooth/tool_call_truncated_synthesized_traj
Viewer • Updated • 4.54k • 10
dogtooth/tool_verify_truncated
Viewer • Updated • 2.85k • 5
dogtooth/math_training_24k
Viewer • Updated • 23.9k • 14
dogtooth/Big-Math-RL-Verified
Viewer • Updated • 1.52M • 55
dogtooth/default_project_dev_test
Viewer • Updated • 4k • 11