solving Github issues with Agentless scaffold and RL
rasdani PRO
rasdani
AI & ML interests
None yet
Recent Activity
authored a paper 1 day ago
Prime Agent: A Self-Improving RLM Harness authored a paper 1 day ago
INTELLECT-3: Technical Report upvoted a paper 1 day ago
Prime Agent: A Self-Improving RLM HarnessOrganizations
models 39
rasdani/Laguna-XS-2.1-Step-1000
33B • Updated
rasdani/Laguna-XS-2.1-Step-1000-GGUF-Q4_K_M
33B • Updated • 6
rasdani/deepseek_r1_qwen14b_swe_rl_8k
15B • Updated • 5 • 1
rasdani/deepseek_r1_llama_8b_swe_rl_8k_12_epochs
8B • Updated • 12 • 1
rasdani/qwen3_8b_swe_rl_8k
8B • Updated • 6
rasdani/deepseek_r1_7b_gh_patches_2k_fixed_reward
8B • Updated • 19
rasdani/deepseek_r1_7b_gh_patches_2k
8B • Updated • 20
rasdani/crux-eval_math-eval-logs
Updated
rasdani/git-diff-Qwen-4B-10k
4B • Updated • 5
rasdani/git-diff-Qwen-4B-10k-checkpoints
Updated
datasets 177
rasdani/deepcoder_eval_claude-sonnet-4-20250514
Viewer • Updated • 16 • 18
rasdani/Code-Contests-Plus-HQ-2x-GRPO
Viewer • Updated • 5.36k • 25
rasdani/Code-Contests-Plus-HQ-1x-GRPO
Viewer • Updated • 4.55k • 48
rasdani/fill-cup-merged
Viewer • Updated • 9.73k • 17
rasdani/SWE-bench_Verified_oracle-parsed_commits_32k_5
Viewer • Updated • 5 • 29
rasdani/SWE-bench_Verified_oracle-parsed_commits_32k_2
Viewer • Updated • 2 • 38
rasdani/SWE-Bench-Verified-R2E-Gym-100
Viewer • Updated • 100 • 19
rasdani/SkyRL-v0-293-data-oracle-4k-context-100-epochs
Viewer • Updated • 7.2k • 14
rasdani/SkyRL-v0-293-data-oracle-8k-context-100-epochs
Viewer • Updated • 13.1k • 17
rasdani/deepseek_r1_llama_8b_swe_rl_8k_12_epochs_preds_100_v2
Viewer • Updated • 100 • 8