github/microsoft-SkillOpt
1
0
Fork 0
mirror of https://github.com/microsoft/SkillOpt.git synced 2026-07-04 14:39:00 +08:00
Code Issues Packages Projects Releases Wiki Activity

Commit Graph

  • 99ec2caf6b docs(sleep): complete 4/4 gbrain parity on Claude AND Codex (tool loop incl.) Yifan Yang 2026-06-08 14:31:51 +00:00
  • acf4545c00 docs(sleep): full 4/4 gbrain parity — quick-answerer 0->1.00 via real tool loop Yifan Yang 2026-06-08 14:31:51 +00:00
  • 1d20e9db14 chore(sleep): include quick-answerer (tool loop) in the sweep direct plan Yifan Yang 2026-06-08 14:31:51 +00:00
  • 937bc1ec4d feat(sleep): real tool-loop replay for gbrain quick-answerer (tool_called judge) Yifan Yang 2026-06-08 14:31:51 +00:00
  • b1f41a7506 docs(sleep): full sweep — 5/5 direct + 4/4 transfer all 0->1.00 Yifan Yang 2026-06-08 14:31:51 +00:00
  • 4186e5bb73 docs(sleep): definitive clean results — Sonnet->Haiku 3/3 seeds 0->1.00 Yifan Yang 2026-06-08 14:31:51 +00:00
  • 023950a291 feat(sleep): sweep 'direct' plan uses strong-optimizer/weak-target dual config Yifan Yang 2026-06-08 14:31:51 +00:00
  • d75863eb6f fix(sleep): retry reflect on non-JSON reply; honest report narrative Yifan Yang 2026-06-08 14:31:51 +00:00
  • c80914b036 fix(sleep): disable global skills in claude calls (--bare --disable-slash-commands) Yifan Yang 2026-06-08 14:31:51 +00:00
  • defb4566ea fix(sleep): isolate claude CLI calls; concrete+override-aware reflect; honor hard constraints Yifan Yang 2026-06-08 14:31:51 +00:00
  • 233b619555 feat(sleep): marketplace manifest, install docs, final report shell, sweep flush Yifan Yang 2026-06-08 14:31:51 +00:00
  • a0419bfdbb feat(sleep): benchmark sweep + report tooling; override-aware reflect prompt Yifan Yang 2026-06-08 14:31:51 +00:00
  • 7d9900b6af feat(sleep): optimizer/target model split, transfer experiment, LLM miner Yifan Yang 2026-06-08 14:31:51 +00:00
  • 63c79b3602 docs(sleep): record real Claude+Codex gbrain results; both reach 0->1.00 Yifan Yang 2026-06-08 14:31:51 +00:00
  • 4203086899 feat(sleep): real claude + codex backends, gbrain-evals benchmark, rule judges Yifan Yang 2026-06-08 14:31:51 +00:00
  • 309f3141d4 docs(sleep): add wake-up summary of the overnight build Yifan Yang 2026-06-08 14:31:51 +00:00
  • 4e7add899d feat(sleep): nightly offline self-evolution engine + Claude Code plugin Yifan Yang 2026-06-08 14:31:51 +00:00
  • 0ac2b35daa docs: add SkillOpt-Sleep Claude Code plugin design Yifan Yang 2026-06-08 14:31:51 +00:00
  • b5328e8b22 Merge pull request #40 from mvanhorn/fix/28-qwen-chat-timeout-and-thinking-tag Yifan Yang 2026-06-08 01:42:50 +08:00
  • c31c50be51 fix(model): forward Qwen timeout and only set enable_thinking when true Matt Van Horn 2026-06-07 07:41:35 -07:00
  • ee9931ec01 docs: add SkillOpt integration news Yif Yang 2026-06-03 16:07:56 +00:00
  • 3f194d58e5 docs: trim News entry wording CharlesYang030 2026-06-02 23:12:40 +08:00
  • c7513d54f3 docs: update News section to match LLM2CLIP style CharlesYang030 2026-06-02 23:09:10 +08:00
  • abc9acd82e docs: add fire emoji to News section heading CharlesYang030 2026-06-02 22:59:06 +08:00
  • 46cc2efd8a docs: add News section, PyPI install instructions, and PyPI badge to README CharlesYang030 2026-06-02 22:54:54 +08:00
  • 25da7cb2dd Merge pull request #32 from Yif-Yang/fix/issue-30-docs-and-template v0.1.0 Ziyang Gong 2026-06-02 10:12:48 +08:00
  • 4eb4c64b2a envs/_template: make template instantiable against real EnvAdapter ABC Yifan Yang 2026-06-01 20:15:12 +00:00
  • 2ca2910649 docs: align API reference and Add-a-Benchmark guide with real EnvAdapter ABC Yifan Yang 2026-06-01 20:14:54 +00:00
  • 4f582d4f6e test: add template contract checks and refine benchmark docs copilot/update-env-adapter-documentation copilot-swe-agent[bot] 2026-06-01 19:39:52 +00:00
  • b3c7d72364 docs: align benchmark guide and templates with real adapter API copilot-swe-agent[bot] 2026-06-01 19:38:17 +00:00
  • 36284e1bb0 Initial plan copilot-swe-agent[bot] 2026-06-01 19:31:30 +00:00
  • fb1a76371d Merge pull request #29 from LifeIsSoSolong/codex/qwen-chat-optimizer-backend Yifan Yang 2026-06-02 03:27:50 +08:00
  • 47063e1ceb Merge pull request #27 from Oxygen56/test/add-core-utility-tests Yifan Yang 2026-06-02 03:27:26 +08:00
  • 181d71b737 Release data split manifests hwq 2026-06-01 16:02:14 +00:00
  • 41012e2d5e Support Qwen chat as optimizer backend kaikai-macbook 2026-06-01 16:44:49 +08:00
  • dd8cd993b5 test: add unit test suite for core utility modules Claude Code Agent 2026-06-01 02:04:22 +08:00
  • 8ebede0efd Refine README for clarity on optimization results Yif Yang 2026-05-31 18:20:00 +08:00
  • 266fca72ab docs: clarify optional features and ckpt artifacts Yif Yang 2026-05-31 09:36:25 +00:00
  • 9265545c45 docs: clarify README and paper-aligned skill artifacts Yif Yang 2026-05-31 09:11:30 +00:00
  • 8acc2dd03e docs: add self-contained reproduction & usage guideline page docs/guideline Cuzyoung 2026-05-31 09:01:25 +00:00
  • b4850ce418 fix(minimax): wire YAML / CLI config through to backend Yif Yang 2026-05-31 08:22:20 +00:00
  • 643346c9f3 Merge pull request #26 from KovaForge/minimax-backend Yif Yang 2026-05-31 08:20:39 +00:00
  • 00602df9e9 feat(slow-update): add config-controlled gated / force-injected modes Cuzyoung 2026-05-31 01:52:02 +00:00
  • c6da31df44 fix: use correct MiniMax endpoint, model name, and add .venv to gitignore Declan Murphy 2026-05-31 05:27:50 +08:00
  • e4201074aa docs: add MiniMax config to default.yaml and .env.example Declan Murphy 2026-05-31 05:22:35 +08:00
  • 309ea64ff4 feat: integrate MiniMax into model router, backend config, and common Declan Murphy 2026-05-31 05:22:33 +08:00
  • d224d425f9 feat: add MiniMax chat backend module Declan Murphy 2026-05-31 05:22:29 +08:00
  • 42e555d28e Update eval-only README example hwq 2026-05-30 15:28:17 +00:00
  • 933c0a4ab5 Add GPT-5.5 benchmark skills hwq 2026-05-30 15:15:15 +00:00
  • 1f75d022a5 y hwq 2026-05-30 15:01:34 +00:00
  • 4f3a9bc055 docs: scope PR #25 gate_metric as opt-in example, not default Yif Yang 2026-05-30 08:09:03 +00:00
  • d190bf37c1 Merge pull request #25 from lvbaocheng/feature/gate-soft-metric Yif Yang 2026-05-30 08:01:39 +00:00
  • 02695bd813 Merge pull request #24 from lvbaocheng/fix/claude-cli-effort-flag Yif Yang 2026-05-30 15:31:00 +08:00
  • cf287cb608 Merge pull request #20 from 1s1x/fix-continuous-reward-scores Yif Yang 2026-05-30 15:30:15 +08:00
  • dbc90bd755 fix(auth): let env vars override yaml for openai_compatible mode Huangzisu 2026-05-30 06:58:05 +00:00
  • 5d7875cb2e Add configurable gate metric (hard / soft / mixed) for skill validation lvbaocheng 2026-05-30 12:46:53 +08:00
  • 2532043d25 fix(claude): use --effort instead of deprecated --thinking flag lvbaocheng 2026-05-30 11:24:13 +08:00
  • 41be2f1803 fix(scoring): use float() instead of int() for continuous reward scores zq 2026-05-30 07:47:41 +08:00
  • a62ec857f1 fix(reflect): support continuous reward scores in failure filtering zq 2026-05-29 19:04:42 +08:00
  • afb552008b fix(trainer): support continuous reward scores in bucket aggregation zq 2026-05-29 19:03:52 +08:00
  • 75b5c7f31c Merge pull request #16 from guilhermeleste/feat/pioneer-ai-provider-integration Yif Yang 2026-05-29 10:14:32 +08:00
  • 74ea3a1a8f Merge pull request #18 from yong2bba/docs/custom-env-smoke Yif Yang 2026-05-29 10:12:55 +08:00
  • 657b987de6 docs: add local environment smoke test guide yongjin 2026-05-29 09:26:38 +09:00
  • 2a40aa3c98 Add SearchQA id split hwq 2026-05-28 11:29:59 +00:00
  • 786d57b5cf Make rollout completion tokens configurable hwq 2026-05-28 09:45:47 +00:00
  • d5c5b61830 Add OpenAI-compatible backend support for Pioneer.ai and other providers guilhermeleste 2026-05-28 05:54:43 -03:00
  • 99212e3956 docs: remove Star History section for now Cuzyoung 2026-05-26 08:12:51 +00:00
  • fc54c44e93 docs: add Star History chart to README Cuzyoung 2026-05-26 08:10:16 +00:00
  • 48adf5a69f Update citation format in README.md Yif Yang 2026-05-26 02:56:58 +08:00
  • b11e6dcfb9 Enhance training description in README Yif Yang 2026-05-26 02:35:10 +08:00
  • 4c1b74fce2 Update BibTeX entry in index.html Yif Yang 2026-05-25 14:30:01 +08:00
  • db6443384a Update BibTeX entry for SkillOpt publication Yif Yang 2026-05-25 14:28:13 +08:00
  • 2c7d9074fb update webpage for arxiv link Huangzisu 2026-05-25 05:32:04 +00:00
  • c98bcdd5b3 Update README.md Yif Yang 2026-05-25 13:27:40 +08:00
  • 0f6db9afc4 Update README.md Yif Yang 2026-05-25 13:26:55 +08:00
  • 5a36ac35ae Merge pull request #7 from microsoft/users/GitHubPolicyService/a41a3ce1-e5a1-4e18-810b-cfb8d2d21c29 Yif Yang 2026-05-25 13:09:26 +08:00
  • 5f4b228543 Soften average gain column styling Lliar-liar 2026-05-24 19:45:10 +00:00
  • a9cad7a125 Use official arXiv logomark Lliar-liar 2026-05-24 19:43:19 +00:00
  • 5e968115f5 Align citation section with SkillLens Lliar-liar 2026-05-24 19:39:16 +00:00
  • ded8c27c90 restore: bring back project page HTML and assets Cuzyoung 2026-05-24 19:38:34 +00:00
  • f55a26414e cleanup: remove unused benchmarks, deep_probe, meta_reflect Cuzyoung 2026-05-24 19:36:27 +00:00
  • 2df2542aec Stabilize skill evolution layout Lliar-liar 2026-05-24 19:36:08 +00:00
  • faa4ec6199 Align header and scroll effects with SkillLens Lliar-liar 2026-05-24 19:31:24 +00:00
  • cff7ff6846 fix: rename remaining teacher/student refs, remove .gradio from repo Cuzyoung 2026-05-24 19:22:20 +00:00
  • 7ae2d8766e docs: restore clean README with Install/Data/QuickStart/WebUI/Citation only Cuzyoung 2026-05-24 19:19:12 +00:00
  • 338a88d31c Add model logos to results table Lliar-liar 2026-05-24 19:18:57 +00:00
  • 4a1b984d87 refactor: rename teacher/student to optimizer/target, remove best skills, fix slow update Cuzyoung 2026-05-24 19:15:03 +00:00
  • 6e165d5347 Add Microsoft favicon Lliar-liar 2026-05-24 19:14:33 +00:00
  • dde7dc9dd8 Add SkillLens related project link Lliar-liar 2026-05-24 19:12:27 +00:00
  • cd9a0a02b9 Restyle project page after SkillLens Lliar-liar 2026-05-24 19:08:05 +00:00
  • 607bf74a1b Reorder hero evaluation stats Lliar-liar 2026-05-24 18:52:05 +00:00
  • 9605217e75 Use Microsoft logo in page header Lliar-liar 2026-05-24 18:27:25 +00:00
  • c42d541828 Refine project links and citation section Lliar-liar 2026-05-24 18:24:48 +00:00
  • 2e05edc399 Add project links and citation section Lliar-liar 2026-05-24 18:18:36 +00:00
  • 6e7d5d0117 Clarify hero harness names Lliar-liar 2026-05-24 18:15:35 +00:00
  • 441ccb9bda Update README.md Yif Yang 2026-05-25 02:15:02 +08:00
  • 88a99048a4 Align method comparison chart with page theme Lliar-liar 2026-05-24 18:05:23 +00:00
  • bf2106808e Remove method comparison implementation caption Lliar-liar 2026-05-24 18:03:21 +00:00
  • ba0fa8c14b Render method comparison from raw data Lliar-liar 2026-05-24 18:00:08 +00:00
  • 9012a79827 Add main results method comparison chart Lliar-liar 2026-05-24 17:55:22 +00:00