cs.AIOct 16, 2026
SaveSkillBrowser: Selective Skill Exposure for Scalable Skill-Using Agents
Organizations: Nanjing University, School of Information Science and Technology
Abstract
Large language model agents increasingly rely on skills to extend their capabilities in complex tasks. However, scalable skill use requires Selective Skill Exposure (SSE): providing relevant procedural content when needed while avoiding unnecessary exposure that may disrupt reasoning. Existing paradigms fall short in complementary ways. Progressive disclosure exposes metadata for a growing skill library, introducing context pollution; retrieval limits catalog exposure, but static retrieval from the initial task query may be misaligned with capability needs that emerge during reasoning and may still inject unnecessary skills. We propose SkillBrowser, a Meta-Skill-managed framework that enables an agent to identify current capability needs, formulate targeted queries, and selectively load skills on demand. Across six SRA-Bench subsets and five LLMs, SkillBrowser improves aggregate accuracy over static retrieval and LLM-based selection, including multi-step tool use, and mitigates accuracy degradation on already-solvable instances. Benefits remain model- and task-dependent, with under-invocation of useful skills and additional latency as key limitations. These results demonstrate the viability of Meta-Skill-managed SSE for scalable skill repositories.
Figures & tables
Figure 1: Motivating example of Skill access over a large repository. (a) Progressive disclosure exposes excessive Skill metadata to the agent and distracts it from loading the required Skill, while (b) static retrieval is misled by a noisy user query. (c) SkillBrowser lets the agent formulate a capability-oriented query and retrieve the required Skill on demand, enabling a correct solution.
Figure 2: Effect of scaling the number of exposed skill descriptions under progressive disclosure.
| Method | Theo. | Logic | CHAMP | MedCalc | BigCode |
| Qwen3-8B GL | 99.3 | 100.0 | 98.7 | 100.0 | 99.1 |
| Qwen3.6-Plus GL | 99.5 | 98.5 | 100.0 | 100.0 | 92.6 |
| BM25 R@ | 77.7 | 28.7 | 30.7 | 66.3 | 96.5 |
| SkillGrep R@ | 82.0 | 31.7 | 32.1 | 81.3 | 86.9 |
Table 1: Comparison between agent-side gold-skill identification and static retrieval from the original task query under a skill library of size . GL denotes the gold-skill loading rate, and R@ denotes Recall@ .
Figure 3: Overview of SkillBrowser . A reusable Meta-Skill enables the agent to decide whether external procedural support is needed and, when necessary, formulate a retrieval intent for SkillGrep . Only selected Skills are introduced into the agent–environment interaction loop.
| Model | Method | Theo. | Logic | CHAMP | MedCalc | BigCode | ToolQA |
| Qwen3-8B | SkillBrowser | 71.0 | 79.5 | 68.2 | 65.4 | 46.7 | 44.0 |
| Static SkillGrep | 61.7 | 72.0 | 69.0 | 60.6 | 46.7 | 17.0 | |
| Static BM25 | 53.0 | 72.0 | 67.3 | 51.4 | 45.8 | 17.0 | |
| LLM Selection | 56.0 | 80.0 | 61.0 | 71.0 | 42.0 | 13.0 | |
| Gold Exposure | 58.9 | 87.0 | 66.8 | 75.0 | 50.0 | 51.0 | |
| Qwen3.6-Plus | SkillBrowser | 84.5 | 84.1 | 81.2 | 93.0 | 61.0 | 57.0 |
Table 2: End-task accuracy (%). Static SkillGrep shares the retrieval backend of SkillBrowser . LLM Selection selects from a BM25 top-50 set. Gray rows denote Gold Exposure, a relevance-controlled reference rather than an upper bound.
| Exposure (%) | Accuracy (%) | ||||
| Model | SB. | SG. | SB. | SG. | |
| Skill-Beneficial ( exposure; accuracy) | |||||
| Qwen3-8B | 74.9 | 100.0 | 67.1 | 67.1 | 859 |
| Qwen3.6-Plus | 80.3 | 100.0 | 76.2 | 77.4 | 336 |
| GLM-5.1 | 84.0 | 100.0 | 85.3 | 77.1 | 556 |
| GPT-5.4-mini | 30.3 | 100.0 | 46.2 | 72.4 | 145 |
Table 3: Selective Skill Exposure analysis aggregated across the four diagnostic benchmarks (TheoremQA, LogicBench, CHAMP, and MedCalcBench). SB. denotes the full SkillBrowser pipeline and SG. denotes static SkillGrep retrieval. Blue-shaded bold values indicate the better accuracy between the two methods. Full model–benchmark results are provided in Appendix C .
| Exposure | Retriever | Theo. | Logic | CHAMP | MedCalc |
| Static | BM25 | 74.42 | 73.20 | 74.00 | 74.66 |
| Static | SG. | 76.12 | 78.32 | 76.40 | 78.96 |
| Meta | BM25 | 75.52 | 74.32 | 71.40 | 77.66 |
| Meta | SG. | 80.00 | 77.78 | 75.62 | 83.42 |
Table 4: Component analysis averaged across backbone models, measured by end-task accuracy (%). Static and Meta denote static exposure and Meta-Skill-managed exposure, respectively; SG. denotes SkillGrep . Meta + SG. is the full SkillBrowser framework. Blue-shaded values indicate the best result in each column.
Appendix figures & tables12 assets
Supplementary material from the paper’s appendix.
Appendix
| Benchmark | Capability Type | # Inst. | # Skills | Evaluation |
| TheoremQA | Theorem application | 747 | 320 | Single, rule-based |
| LogicBench | Logical reasoning patterns | 760 | 19 | Single, rule-based |
| CHAMP | Mathematical concepts | 223 | 89 | Multi, rule-based |
| MedCalcBench | Medical calculators | 1,100 | 55 | Single, rule-based |
| BigCodeBench | Software libraries | 1,140 | 139 | Multi, execution-based |
| Subtotal | – | 3,970 | 622 | – |
Table 5: Source statistics for the five original SRA-Bench subsets; ToolQA evaluation counts are reported separately. The complete retrieval corpus additionally contains web-collected distractor skills, resulting in 26,262 candidate skills in total.
| Benchmark | Query Example | Gold Skill Name |
|---|---|---|
| TheoremQA | How many ways are there to divide a set of 8 elements into 5 non-empty ordered subsets? | Lah Numbers |
| LogicBench | If an individual decides to take a temporary break from their professional responsibilities, it can contribute to their overall sense of rejuvenation. however, if they choose to burden themselves with additional tasks, they may find themselves feeling overwhelmed. in this scenario, we are aware that at least one of the following statements holds true: (1) mike takes a break from work, or (2) he do not experience overwhelming feelings. it is important to note that we lack knowledge regarding which one, or both, of these statements are accurate. In light of the context provided, what conclusion can be considered the most appropriate? choice_1: Luke takes a break from work and feels refreshed. choice_2: Mike takes on more tasks and feels overwhelmed. choice_3: Mike takes a break from work and feels overwhelmed. choice_4: he will feel refreshed or he doesn’t take on more tasks | Bidirectional Dilemma |
| CHAMP | Let a string consist of digit 1, 2, 3. How many such strings of length 6 have adjacent digit differing by less than or equal to 1? | Rule of Sum (Addition Principle) |
| BigCodeBench | Calculates the average of the sums of absolute differences between each pair of consecutive numbers for all permutations of a given list. Each permutation is shuffled before calculating the differences. Args: – numbers ( list ): A list of numbers. Default is numbers from 1 to 10. The function should output with: float : The average of the sums of absolute differences for each shuffled permutation of the list. You should write self-contained code starting with: import itertools from random import shuffle def task_func(numbers=list(range(1, 3))): | random – Core API and Common Patterns; itertools – Iterator Building Blocks |
| MedCalcBench | Patient Note: An 87-year-old man was admitted to our hospital for anorexia for several days, high-grade fever from the previous day, and liver dysfunction. Of note, he had a history of hypertension, diabetes mellitus (DM), and angina. Physical examination findings included: clear consciousness; height, 163 cm; weight, 48 kg; blood pressure, 66/40 mmHg; heart rate, 75/min; respiratory rate, 22/min; oxygen saturation of peripheral artery, 96%; and body temperature, 38.1 °C. He had no surface lymphadenopathy. Laboratory findings included: white blood cell (WBC) count, 4.2 × 109/L; hemoglobin, 9.6 g/dL; platelet count, 106 × 109/L; lactate dehydrogenase (LDH), 1662 IU/L; aspartate aminotransferase (AST), 6562 IU/L; alanine aminotransferase (ALT), 1407 IU/L; alkaline phosphatase (ALP), 509 IU/L; -glutamyl transpeptidase ( -GTP), 130 IU/L; total bilirubin, 2.7 mg/dL; prothrombin time (PT), 20.3 s; international normalized ratio (INR), 1.73; blood urea nitrogen (BUN), 34.4 mg/dL; and creatinine, 1.4 mg/dL. Serologic tests were all negative for hepatitis A, B, C, and E. Computed tomography (CT) performed at admission revealed no distinct nodules or masses in the liver, but mild splenomegaly, multiple hypodense splenic lesions, and para-aortic lymph node swelling (Fig. a–c). Antibiotics were administered intravenously for suspected acute cholangitis and sepsis, but the fever persisted. Abdominal ultrasonography (US) and magnetic resonance imaging (MRI) performed 2 days later newly depicted gallbladder wall thickening and ascites (Figs. , ). On the same night, the patient presented with grade II hepatic encephalopathy, with blood tests showing a decrease in platelet count and worsening liver function suggestive of “acute type” ALF with hepatic coma and disseminated intravascular coagulation (DIC). While consideration was being given to treating acute liver failure, the patient suddenly developed ventricular fibrillation and died despite immediate resuscitation measures on day 3 of hospitalization. Given the rapid clinical course, an autopsy was performed in this patient with suspected ALF likely due to drug-induced liver injury, autoimmune hepatitis, hepatitis of indeterminate etiology, circulatory disturbance, metabolic disease, or malignant cells including malignant lymphoma. This led to the patient being diagnosed with malignant, diffuse large B-cell lymphoma, characterized by multiple lymph-node, as well as multi-organ (i.e., spleen, liver, lung, and prostate) involvement: (1) general swelling of lymph nodes in the para-abdominal aorta (Fig. a), peripancreatic, peribronchial, pulmonary hilar, subclavicular regions, as well as in the pelvis, especially around the iliac arteries, measuring up to 60 mm in diameter; (2) presence of multiple whitish splenic nodules (Fig. b) with the entire spleen shown to be microscopically infiltrated by tumor cells (Fig. a); (3) irregular geographical morphology of the liver (Fig. c) with the lymphoma cells mainly infiltrating the portal areas (Fig. b); (4) involvement of the right lobe of the lung; (5) involvement of both lobes of the prostate consequent to outer connective tissue involvement (Fig. c). Microscopically, the tumor cells in the lymph nodes were shown to have medium-sized irregular nuclei and small nucleoli with a high nuclear cytoplasmic ratio, thus showing diffuse proliferation characterized by the presence of large numbers of small T-cells (Fig. ). Immunohistochemistry revealed the tumor cells to be positive for CD20 (Fig. a), CD79a (Fig. b), bcl-2 (Fig. c), and MUM1 (Fig. d), but negative for CD3 (Fig. e), CD10, bcl-6, and cyclin D1, with a Ki-67 labeling index (Ki-67 LI) of 16% (Fig. f). The causes of death were thus determined as (1) DIC and (2) ALF associated with diffuse large B-cell lymphoma. Task: What is the patient’s Creatinine Clearance using the Cockroft-Gault Equation in terms of mL/min? You should use the patient’s adjusted body weight in kg instead of the patient’s actual body weight if the patient is overweight or obese based on their BMI. If the patient’s BMI’s normal, set their adjusted body weight to the minimum of the ideal body and actual weight. If the patient is underweight, please set their adjusted body weight to their actual body weight. You should use the patient’s medical values and health status when they were first admitted to the hospital prior to any treatment. | Creatinine Clearance (Cockcroft–Gault Equation) |
Table 6: Representative instances and their annotated gold skills from the five SRA-Bench subsets used in our evaluation. Complete queries are retained without truncation.
| Model | Benchmark | #Ben. | BER | Accuracy | ||
| Meta-Skill | SkillGrep | Meta-Skill | SkillGrep | |||
| Qwen3-8B | CHAMP | 59 | 59.3 | 100.0 | 67.8 | 78.0 |
| LogicBench | 144 | 77.8 | 100.0 | 53.5 | 50.0 | |
| MedCalcBench | 444 | 64.0 | 100.0 | 60.4 | 64.2 | |
| TheoremQA | 212 | 100.0 | 100.0 | 90.1 | 81.6 | |
| Qwen3.6-Plus | CHAMP | 15 | 26.7 | 100.0 | 33.3 | 53.3 |
Table 7: Full results on skill-beneficial instances. These instances are answered incorrectly without external Skills but correctly when the annotated gold Skill is provided. BER denotes Beneficial Exposure Rate, i.e., the percentage of instances on which retrieved Skill contents are exposed.
| Model | Benchmark | #Unn. | UER | Accuracy | ||
| Meta-Skill | SkillGrep | Meta-Skill | SkillGrep | |||
| Qwen3-8B | CHAMP | 90 | 36.7 | 100.0 | 94.4 | 91.1 |
| LogicBench | 517 | 72.9 | 100.0 | 92.8 | 83.0 | |
| MedCalcBench | 381 | 45.4 | 100.0 | 97.6 | 86.9 | |
| TheoremQA | 228 | 99.1 | 100.0 | 96.9 | 86.0 | |
| Qwen3.6-Plus | CHAMP | 173 | 31.2 | 100.0 | 98.8 | 97.7 |
Table 8: Full results on skill-unnecessary instances. These instances are answered correctly both without external Skills and with the annotated gold Skill. UER denotes Unnecessary Exposure Rate, i.e., the percentage of instances on which retrieved Skill contents are exposed although they are not necessary for correctness under the evaluated model.
| Retriever | GoldHit@5 | GoldMRR@5 | Recall@1 | Recall@5 | nDCG@1 | nDCG@5 |
| SKILLGREP | 0.62 | 0.50 | 0.40 | 0.59 | 0.43 | 0.51 |
| SR-Agent BGE Retriever | 0.47 | 0.37 | 0.31 | 0.45 | 0.31 | 0.39 |
| SR-Agent TF-IDF | 0.39 | 0.29 | 0.22 | 0.37 | 0.23 | 0.30 |
| SR-Agent BM25 | 0.49 | 0.36 | 0.28 | 0.46 | 0.30 | 0.38 |
| SR-Agent Contriever | 0.41 | 0.31 | 0.24 | 0.39 | 0.24 | 0.32 |
Table 9: Static retrieval over the full Skill corpus using original task descriptions as queries. Values are proportions, reported at the reported precision; bold marks the best result.
| Variant | GoldHit@5 | GoldMRR@5 | Recall@1 | Recall@5 | nDCG@1 | nDCG@5 |
| Full SKILLGREP | 0.623 | 0.500 | 0.402 | 0.590 | 0.429 | 0.511 |
| No Penalty | 0.623 | 0.500 | 0.401 | 0.590 | 0.429 | 0.511 |
| No RRF Score | 0.578 | 0.471 | 0.381 | 0.544 | 0.408 | 0.477 |
| No Sparse View | 0.548 | 0.446 | 0.359 | 0.514 | 0.383 | 0.452 |
| No Dense | 0.463 | 0.422 | 0.364 | 0.436 | 0.392 | 0.413 |
| No Capability/Type Signals | 0.462 | 0.431 | 0.379 | 0.436 | 0.407 | 0.420 |
Table 10: Leave-one-component-out SkillGrep ablation. All values are proportions; bold marks the best results, including ties at the reported precision.
| Model | Method | Accuracy | Recall@5 | Search | R@5/Search |
| Qwen3-8B | Static BM25 | 0.17 | 0.00 | 1.00 | 0.00 |
| Static SKILLGREP | 0.17 | 0.00 | 1.00 | 0.00 | |
| SKILLBROWSER | 0.44 | 0.50 | 0.93 | 0.54 | |
| Gold Exposure | 0.51 | - | - | - | |
| Qwen3.6-Plus | Static BM25 | 0.32 | 0.00 | 1.00 | 0.00 |
| Static SKILLGREP | 0.27 | 0.00 | 1.00 | 0.00 |
Table 11: ToolQA accuracy and retrieval behavior (proportions), with 100 valid trajectories per model. Dashes indicate that search metrics do not apply to direct gold exposure.
| Model | SkillBrowser | Gold Exposure | LLM Selection |
| Qwen3-8B | 8.66 | 4.30 | 5.30 |
| Qwen3.6-Plus | 8.60 | 6.80 | 6.90 |
| GLM-5.1 | 5.35 | 3.30 | 6.70 |
| GPT-5.4-mini | 5.96 | 3.30 | 5.50 |
| Gemini-3.1-Flash-Lite | 5.40 | 2.20 | 4.80 |
Table 12: Average total LLM calls per ToolQA instance.
| Benchmark | SkillBrowser | Gold Exposure | LLM Selection |
| TheoremQA | 3014.1 / 947.7 | 1095.6 / 419.4 | 4035.1 / 411.9 |
| LogicBench | 6014.4 / 1714.3 | 1392.1 / 527.3 | 4661.2 / 563.5 |
| CHAMP | 3372.4 / 3850.1 | 1857.9 / 693.7 | 6319.6 / 879.3 |
| MedCalcBench | 3395.4 / 797.6 | 1489.8 / 278.6 | 6120.9 / 293.6 |
| ToolQA | 44569.1 / 798.5 | 16279.7 / 214.1 | 40386.3 / 982.5 |
| BigCodeBench | 1627.2 / 627.7 | 4827.5 / 272.4 | 4492.0 / 301.9 |
Table 13: Average GLM-5.1 input / output tokens per instance over the complete trajectory.
| Benchmark | SkillBrowser | Gold Exposure | LLM Selection |
| TheoremQA | 23.384 | 8.601 | 10.055 |
| LogicBench | 42.356 | 14.203 | 14.582 |
| CHAMP | 63.435 | 10.357 | 16.785 |
| MedCalcBench | 31.063 | 9.881 | 11.148 |
| ToolQA | 36.937 | 18.500 | 33.139 |
| BigCodeBench | 19.050 | 5.649 | 7.427 |
Table 14: Average GLM-5.1 latency in seconds per instance. LLM Selection excludes precomputed BM25 retrieval; SkillBrowser includes online retrieval and Skill loading.
| Gold Exposure | SkillBrowser | Share (%) |
| Incorrect | Correct | 5.0 |
| Correct | Correct | 72.1 |
| Correct | Incorrect | 9.9 |
| Incorrect | Incorrect | 12.9 |
Table 15: Correctness transitions, macro-averaged across 30 model–dataset settings.
| Comparator | SB acc. | Ref. acc. | ||||
| Static SkillGrep | 78.59 | 74.64 | 11,736 | 1,110 | 647 | |
| LLM Selection | 75.93 | 72.82 | – | 646 | 440 | |
| Gold Exposure | 78.59 | 80.52 | – | 692 | 920 |
Table 16: Pooled valid-pair accuracy (%) and two-sided exact McNemar tests. / count exclusive SkillBrowser/comparator wins. Dashes denote paired sample sizes unavailable in the aggregate statistics; they must not be assumed equal across comparators.
More in this topic
LLM Agent Skill Retrieval
Large language model agent skill retrieval finds and selects reusable procedures to help agents complete tasks.
See all 102 papers