Skill Adapter Study (Qwen3-8B executor) - ALFWorld Overall Success Rate: leaderboard

Benchmarks and budgets: ALFWorld 420 test tasks / 50 steps (six task types); WebShop 1,500 tasks / 15 steps; SkillsBench 210 tasks / 30 steps (Experimental Setup). Executors: Qwen3-8B (ALFWorld, WebShop), GPT-5-mini (SkillsBench); frozen; shared by all methods within a benchmark (Experimental Setup). Skill pools: GPT-5.2-Codex-extracted skills from clustered AgentTraj-L trajectories (ALFWorld, WebShop); merged benchmark-provided skills (SkillsBench) (Experimental Setup). Retrieval (Skill Adapter): BGE-M3 embeddings; 3 topics, 20 skills, expansion capped at 30 candidates; router selects at most 8 skills (Experimental Setup). Metrics: ALFWorld per-type and overall SR, mean time; WebShop task score, SR, mean time; SkillsBench SR, mean reward, mean time (Experimental Setup, Metrics). Runs: Seeds 42, 43, 44; main tables report the mean of three runs (Experimental Setup). Decoding, thinking mode (Qwen3-8B), reasoning effort and snapshot (GPT-5-mini): not stated (not stated). Board structure: Each benchmark has a single executor identity, so every admissible board ranks configurations of one model; under the per-board harness fold these boards reduce to one model row and carry no cross-model ranking signal. Materialize only if single-identity configuration boards are kept. (reviewer note). This board: 420 ALFWorld test tasks overall (per-type counts not printed); Mean over three runs (seeds 42, 43, 44). ALFWorld test set as used by the paper (420 tasks); version not stated. Metric: Task success rate (%) on ALFWorld Higher is better.

Metric: Task success rate (%) on ALFWorld. Source: arxiv.org. Saturation forecast: Rough model projection: around 2026. 1 model tracked. Updated 14 Nov 2026.

Top models

#ModelSettingScoreOverall rank
1Qwen3-8BSkill Adapter run: Backbone + BM2561.67

Interactive version: theaggregate.ai/benchmark?slug=skill-adapter-study-qwen3-8b-executor-alfworld-overall-success-rate · How It Works · Data refreshed daily, snapshot 2026-11-16.