趋势解读：Microsoft's SkillOpt boosts GPT-5.5 by using nothing but，聚焦形式化数学证明能力

A simple Markdown file is apparently enough to boost GPT-5.5 by more than 20 points on procedural tasks. That's the promise of SkillOpt, a method from Microsoft and three Chinese universities that trains instruction documents for AI agents the same way model weights get trained. These kinds of instruction documents, known as "skills," are already common in commercial products. Anthropic, for example, added a modular skill system to Claude last year that automatically loads topic-specific instructions, scripts, and resources depending on the task. Skills typically bundle procedures, tool-use rules, output formats, and known failure patterns, and they've become a standard approach . Until now, according to the Microsoft team's paper, they were either written by hand, generated in a single pass by a language model, or loosely self-revised. None of these approaches behaves like a real optimizer, and none guarantees the skill actually improves. SkillOpt treats the skill document as an external, trainable state for a frozen target model. A second, separate language model acts as the optimizer. It reads logs from the agent's runs, spots recurring error and success patterns, and proposes limited edits to the skill: adding, deleting, or replacing individual passages. Each change is only accepted if it performs better on a held-out validation set. The authors map several deep learning concepts onto the text level. A kind of learning rate caps how many edits can land per step. A scheduler shrinks the step size across epochs. Rejected edits go into a buffer and serve as negative examples for later reflection. A slow update at the end of each epoch preserves stable edit directions across training rounds, similar to how gradient smoothing works in traditional training. What makes this practical is the clean split between training and deployment. The optimizer model only runs during training, and once that's done, it's out of the picture. At inference time, the target model simply receives a plain Markdown file of 300 to 2,000 tokens as context. The authors tested their approach on six benchmarks covering search, spreadsheets, document analysis, math, and embodied action. Seven systems served as target models, including GPT-5.5 and the much smaller Qwen3.5-4B. Tasks ran in direct chat as well as in the agent environments Codex and Claude Code. Across every combination, SkillOpt leads or ties with the best comparison result. That holds against handwritten skills, one-shot LLM-generated skills, and specialized methods like Trace2Skill, TextGrad, GEPA, and EvoSkill. On GPT-5.5 in direct chat, the average across all six benchmarks jumps by about 23 points. The biggest gains show up on tasks with strict format requirements and tool use, like spreadsheet editing. Smaller models benefit too, which the authors take as evidence that a well-trained skill delivers procedural knowledge these models lack in their weights. One key finding is transferability. A skill trained on a larger model also improves smaller models in the same family. A spreadsheet skill trained in the Codex loop works unchanged in Claude Code, lifting performance there to the same level as a skill trained directly in Claude Code. A math skill optimized on olympiad problems still delivers gains on a related benchmark without any retraining. The ablation studies explain why the method stays stable. Without a bounded edit budget, the skill drifts too far with each revision. Without the buffer for rejected edits, the optimizer repeats the same failed attempts. Removing the slow update at epoch's end costs SpreadsheetBench more than twenty points, the largest drop in the entire experiment. Only the combination of bounded step size, validation gating, negative feedback, and long-term consolidation makes skill training behave like a controlled optimization process, the authors say.