skillfed

Compiling a skill per task beats a static library by up to 13 Pass@1 points

Notes on Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents (arXiv:2605.16986) — Jingxing Wang, Chenyue Zhou, Zhihui Fu, Jun Wang, Weiwen Liu, Weinan Zhang, Jianghao Lin · May 2026

Note published · written by SkillFed’s research pipeline from the paper above · how these notes are made

AI-assisted notes · reviewed by SkillFed Skill evolution Bridge: evolution × retrieval

SkillTTA treats skill-building as test-time adaptation: instead of shipping one skill per task family, it keeps a pool of past training trajectories, both successes and failures, tagged with lightweight, answer-free task metadata. At test time it embeds the incoming task and does trajectory retrieval, pulling a small top-k set of the most similar past runs by cosine similarity. A synthesis model then turns the current task plus that retrieved evidence into a one-off skill file, covering when to use it, likely failure modes, and non-prescriptive procedure notes, that a fixed solver conditions on for that single task; no weights change. Benchmarks pit this against a static skill library baseline that synthesizes one skill per trajectory cluster and reuses it as-is, plus a memory-learning baseline that updates through repeated interaction, across spreadsheet editing (SpreadsheetBench), household tasks (ALFWorld), and code generation (BigCodeBench).

Against the static-skill baseline, task-specific synthesis raises SpreadsheetBench Pass@1 from 0.397 to 0.505 and BigCodeBench Pass@1 from 0.517 to 0.651 — roughly 11 and 13 points respectively. On ALFWorld it lands within about 3.5 points of success rate of the memory-learning baseline (0.872 versus 0.907), while finishing successful episodes in fewer steps than any other method tested, including that baseline. Ablations on SpreadsheetBench show why. Synthesizing a skill from retrieved trajectories beats simply prompting with the raw trajectories (0.540 versus 0.422 Pass@1). Retrieval should stay narrow: top-3 beats top-5 and top-9. And restricting retrieval to failed trajectories beats mixing in successes, because failures name the specific, recurring mistakes an evaluator penalizes.

Key numbers

SpreadsheetBench Pass@1, static skill vs. per-task skill0.397 → 0.505
BigCodeBench Pass@1, static skill vs. per-task skill0.517 → 0.651
ALFWorld success-rate gap vs. memory-learning baseline0.872 vs 0.907 (~3.5 pts)
Synthesized skill vs. raw trajectory prompting (Pass@1)0.540 vs 0.422
Retrieval depth where accuracy peakstop-3 best; k=5, k=9 underperform

Skills related to this research

Related notes

References

  1. Wang, J., Zhou, C., Fu, Z., Wang, J., Liu, W., Zhang, W., Lin, J. (2026). Skills on the Fly: Test-Time Adaptive Skill Synthesis for LLM Agents. arXiv:2605.16986.
  2. Yao, S. et al. (2022). ReAct: Synergizing Reasoning and Acting in Language Models.
  3. Shinn, N. et al. (2023). Reflexion: Language Agents with Verbal Reinforcement Learning.
  4. Wang, G. et al. (2023). Voyager: An Open-Ended Embodied Agent with Large Language Models.
  5. Zhao, A. et al. (2023). ExpeL: LLM Agents Are Experiential Learners.