SWE-Milestone
[ICML 2026] Evaluating AI Agents on Continuous Software Evolution
파일 탐색기
최종 버전 다운로드 (.zip)- tests.yml
- verify-image-digests.yml
- banner.png
- milestone_dag_sklearn.svg
- swe-milestone_arch.png
- swe-milestone_concept.png
- swe-milestone_example.png
- swe-milestone_icon.png
- swe-milestone_illustration.pdf
- swe-milestone_illustration.png
- infra-failure-audit.md
- prune-config-authoring.md
- re-evaluation-playbook.md
- adding-a-repo.md
- env-deps-verification.md
- image-patching.md
- re-evaluation.md
- README.md
- residue-prune-spec.md
- scoring-id-identity-fix.md
- v1.0.2-release-plan.md
- adding-a-model.md
- advanced.md
- quarantine.md
- README.md
- running-trials.md
- setup.md
- versioning.md
- vertex-ai.md
- __init__.py
- base.py
- claude_code.py
- codex.py
- gemini.py
- openhands.py
- jest_ipc_guard.js
- __init__.py
- base.py
- classify_behavior.py
- claude_code.py
- codex.py
- gemini.py
- models.py
- openhands.py
- verification.py
- milestone_v1.md
- v1.md
- v1_recover.md
- v2.md
- v2_recover.md
- v2_recover.md.tmpl
- __init__.py
- agent_runner.py
- collect_results.py
- config.py
- container_setup.py
- dag.py
- data_version.py
- e2e_config.yaml
- env_guard.py
- evaluator.py
- image_version.py
- milestone_selection.py
- model_aliases.py
- orchestrator.py
- pricing.py
- quarantine.py
- repo_config_binding.py
- rescore.py
- residue_prune.py
- resume.py
- run_e2e.py
- run_milestone.py
- runtime_policy_binding.py
- sni_tunnel.py
- test_masking.py
- trial_lock.py
- trial_metrics.py
- __init__.py
- agent_runner.py
- analyzer.py
- cli.py
- git_utils.py
- hunk_classifier.py
- main.py
- models.py
- patch_fixer.py
- patch_generator.py
- patch_parser.py
- prompts.py
- README.md
- test_detector.py
- verifier.py
- verify_test_separation.py
- __init__.py
- __init__.py
- classifier.py
- docker.py
- merger.py
- milestone_attempt.py
- report_parser.py
- test_executor.py
- types.py
- __init__.py
- milestone_runner.py
- __init__.py
- run_milestone_tests.py
- single_state_runner.py
- __init__.py
- cargo_report_utils.py
- django_report_utils.py
- go_report_utils.py
- maven_report_utils.py
- maven_surefire_xml_utils.py
- pytest_report_utils.py
- rust_test_filter.py
- snapshot.py
- src_filter.py
- test_id_normalizer.py
- __init__.py
- BENCHMARK_VERSION
- digests-v1.0.1.tsv
- digests-v1.0.2.tsv
- digests-v1.0.tsv
- apache_dubbo_dubbo-3.3.3_dubbo-3.3.6.yaml
- BurntSushi_ripgrep_14.1.1_15.0.0.yaml
- element-hq_element-web_v1.11.95_v1.11.97.yaml
- navidrome_navidrome_v0.57.0_v0.58.0.yaml
- nushell_nushell_0.106.0_0.108.0.yaml
- scikit-learn_scikit-learn_1.5.2_1.6.0.yaml
- zeromicro_go-zero_v1.6.0_v1.9.3.yaml
- build_offline_closure.py
- check_record_consistency.py
- check_test_id_identity.py
- migrate_trial.sh
- monitor.sh
- promote_cells.py
- pull_data.sh
- pull_images.sh
- push_images.sh
- recapture_trial_snapshots.py
- rescore_cells.py
- run_all.py
- verify_env_deps.py
- verify_image_digests.py
- verify_quarantine.py
- navidrome_end_build_output.txt
- navidrome_ginkgo_build_dead_cell.json.gz
- scikit_m121_collection_death_cell.json.gz
- test_agent_prompt.py
- test_agent_version.py
- test_ast_grep_resolution.py
- test_check_record_consistency.py
- test_check_test_id_identity.py
- test_codex_framework.py
- test_collect_results.py
- test_compile_gate_no_waiver.py
- test_container_setup.py
- test_data_version.py
- test_evaluator_compile_fail_closed.py
- test_evaluator_filter.py
- test_ginkgo_golden_replay.py
- test_ginkgo_scoring_observability.py
- test_go_partial_package_filter.py
- test_image_version.py
- test_invocation_kill.py
- test_jest_ipc_guard.py
- test_late_eval_reconcile.py
- test_legacy_snapshot_flag.py
- test_manifest_dedupe.py
- test_masking_fallback.py
- test_milestone_selection.py
- test_module_aware_scoring.py
- test_overload_backoff.py
- test_promote_cells.py
- test_quarantine.py
- test_repo_config_binding.py
- test_rescore.py
- test_rescore_filter_only.py
- test_residue_prune.py
- test_run_milestone_runtime_policy.py
- test_runtime_policy_binding.py
- test_rust_unplaced_roundtrip.py
- test_scikit_collection_death_golden_replay.py
- test_scoring_identity.py
- test_snapshot_fail_closed.py
- test_sni_tunnel.py
- test_summary_status_buckets.py
- test_tool_search_setting.py
- test_watcher_tag_race.py
- test_build_offline_closure.py
- test_run_all_agent_version.py
- test_run_all_runtime_policy.py
- test_verify_env_deps.py
- test_error_surfacing.py
- test_framework_resolution.py
- test_infra_detection.py
- test_go_report_utils.py
- test_rust_test_filter.py
- test_snapshot.py
- claude-code_glm-5.1.yaml
- claude-code_glm-5.2-1m.yaml
- claude-code_glm-5.2.yaml
- claude-code_kimi-k2.6.yaml
- claude-code_opus-4.6.yaml
- claude-code_opus-4.7-1m.yaml
- claude-code_opus-4.7.yaml
- claude-code_opus-4.8-1m.yaml
- claude-code_opus-4.8.yaml
- codex_gpt-5.4.yaml
- codex_gpt-5.5.yaml
- codex_gpt-5.6-sol.yaml
- gemini-cli_gemini-3.5-flash.yaml
- .env
- .gitignore
- LICENSE
- pyproject.toml
- README.md
- trial_config.example.yaml
// repository documentation
Was this content helpful?
(0 ratings)