Collect first agent research and market sources

2026-07-08 12:08:24 +08:00
parent 36c2499d3c
commit 1cbc98e432
34 changed files with 3417 additions and 58 deletions
@@ -0,0 +1,68 @@
+# Industry: Microsoft Research - SkillOpt
+
+---
+type: industry
+company: Microsoft
+team: Microsoft Research
+title: "SkillOpt: Agent skills as trainable parameters"
+url: https://www.microsoft.com/en-us/research/blog/skillopt-agent-skills-as-trainable-parameters/
+source_name: Microsoft Research
+source_type: research-blog
+source_quality: official
+published_at: 2026-06-30
+collected_at: 2026-07-08
+status: analyzed
+topics:
+  - agent
+  - prompt-optimization
+  - skill-learning
+implementation_signals:
+  - skill-files
+  - validation-gating
+  - bounded-edits
+  - eval-loop
+product_area:
+  - agent-framework
+models:
+  -
+tools:
+  -
+benchmarks:
+  - six-benchmark-evaluation
+related_papers:
+  -
+related_jobs:
+  - 2026-07-08-deepseek-agent-hiring-wave-beijing-hangzhou
+related_experiments:
+  -
+related_projects:
+  -
+evidence_level: high
+relevance: high
+---
+
+## One-line Takeaway
+
+Agent skill/prompt 文件可以被当成外部可训练参数，用评估循环优化，而不是靠人工随手改。
+
+## What They Built or Claimed
+
+Microsoft Research 提出 SkillOpt，将 skill editing 转成训练过程，在不改模型权重的情况下提升 Agent 行为可靠性。
+
+## Technical Signals
+
+- architecture: frozen target model + external skill file optimization。
+- tool use:
+- memory:
+- evaluation: 六个 benchmark、七个目标模型、三种执行模式。
+- safety: bounded text edits、validation gating、rejected-edit feedback、slow/meta updates。
+- deployment: 可审计技能文件。
+- data:
+
+## Evidence Quality
+
+官方研究博客给出实验覆盖和机制细节，证据强。
+
+## Gaps for Us
+
+- 可以把本项目的 `skills`、prompt、playbook 也纳入 eval-driven 优化。