Large language model (LLM) agents extend their capabilities with skills, each with a name, a description, and a body. Under progressive disclosure, an LLM router selects skills by name and description alone and loads only the selected bodies. Skill libraries grow continually as users and agents add new skills. Because the router relies on this metadata, a similar new skill can displace an earlier one, breaking previously correct routing even though the earlier skill and the router are unchanged. This routing interference is aggravated for public skills, whose descriptions may not match their bodies. We formulate the problem as lifelong skill routing, a class-incremental continual learning problem. A solution must keep earlier skills selectable without suppressing new ones. Existing approaches fall short, since continually retraining the router risks catastrophic forgetting and rewriting methods either ignore similar skills or require per-skill feedback. We therefore propose Skill++, which rewrites only the name and description of each incoming skill, without router training or labeled data. The new description states what the body supports, how the skill differs from its closest predecessor, and what related work it excludes. As a library grows to 731 skills over ten sessions, Skill++ selects all required skills for 76.3% of queries, versus 36.4% under the original metadata. Across three benchmarks and five LLM routers, it outperforms all compared approaches, and its gains carry over to the Codex CLI agent harness.
Figures & tables
Figure 1: This figure presents an example of routing interference, to show why incoming metadata needs refinement. The router reads only skill names and descriptions. (a) For a query about an AI paper, it selects the AI paper-writing skill. (b) A biology paper-writing skill arrives with the same metadata, and the router selects it instead. (c) Skill++ refines only the incoming skill against the earlier one, so the router selects the correct skill again.
Figure 2: This figure compares three ways of handling a growing skill library, to position our problem. (a) Continuous router training follows arriving skills but retrains the router at every step, risking catastrophic forgetting of earlier skills. (b) One-shot skill optimization refines a fixed skill set once, so it ignores skills that arrive later. (c) Skill++ keeps the router frozen and refines each new batch against similar earlier skills, so both earlier and new skills are selected for the queries that need them.
Figure 3: This figure gives an overview of Skill++ , to show how it refines an incoming skill before the router reads it. Skill++ first retrieves similar earlier skills from a record of their original names, descriptions, bodies and synthetic queries. Three components then refine the new skill independently. Description differentiation rewrites its description around what makes it unique, scope exclusions list related work that it does not cover, and name clarification makes an overlapping name more specific. The refined name and description enter the library that the router reads, and the original skill joins the record for future additions.
Figure 4: This figure shows FC@5 as the library grows (sizes in Tab. A2 ), to test whether routing stays accurate. (a) The main router, Claude Haiku 4.5 (Tab. A1 ). (b)–(e) Four other routers (Tab. A4 ). With every router, Vanilla declines while Skill++ leads or ties at every checkpoint.
Figure 5: This figure breaks down the routing errors at S9 into two forms and seven types (defined in Appendix C.2 ), to show which errors Skill++ removes. All panels draw on the eight combinations of Tab. A3 . (a) The 200 Vanilla errors, by form (inner ring) and type (outer ring). (b) Errors per type under Vanilla and Skill++ , as a share of the Vanilla errors. (c) Errors per form when one component or all three are added to Vanilla, shown in the same way. Skill++ removes most errors of both forms, and each component mainly reduces one form.
Appendix figures & tables11 assets
Supplementary material from the paper’s appendix.
Appendix
Figure A1: This figure compares conventional class-incremental learning with lifelong skill routing, to motivate our formulation. Both settings aim to retain earlier performance while accommodating new classes or skills. (a) The model is trained on new labeled classes, so parameter updates can change its decisions on earlier classes. (b) New skill classes and skills similar to earlier ones arrive while the router stays frozen and reads only names and descriptions. A biology paper-writing skill with the same metadata as the earlier AI skill can push the unchanged AI skill out of the top- K for an earlier query, so Skill++ refines only the metadata of incoming skills.
Approach
S1
S2
S3
S4
S5
S6
S7
S8
S9
Avg
FC@5 (%) ↑ : all required skills in the final selection
Vanilla
92.5
78.3
73.8
68.0
51.7
49.3
44.4
31.8
36.4
58.5
Body-distilled
90.0
80.0
86.2
72.0
68.3
57.1
55.6
47.5
44.4
66.8
Neighbor-contrastive
92.5
85.0
78.8
71.0
61.7
58.6
58.1
53.6
50.0
67.7
R&R
90.0
80.0
75.0
70.0
62.5
60.7
60.0
62.0
58.6
68.8
R&R-CFT
89.2
77.2
79.6
70.3
70.8
67.6
69.4
68.2
67.8
73.3
Appendix
Table A1: FC@5 is the share of queries whose required skills all reach the final selection, and Recall@5 is the share of each query’s required skills that reach it, averaged over queries. The table gives both for every approach at every checkpoint of the main study with Claude Haiku 4.5. Fig. 4 a plots the FC@5 block, and -CFT results average three training seeds. Bold marks the best value per column and block, and underline the second.
Session
Skills in the library / evaluated queries
SRA-Bench
SkillRet
SkillRouter
S1
87 /
40
83 /
12
82 /
8
S2
152 /
60
200 /
18
207 /
11
S3
224 /
80
319 /
24
339 /
15
S4
305 /
100
483 /
30
535 /
19
S5
387 /
120
725 /
36
758 /
23
Appendix
Table A2: This table gives the library size and the number of evaluated queries at every checkpoint, to compare how the three benchmarks grow. The evaluated queries are all queries released so far.
Figure A2: Each bar splits the S9 queries of one approach by the stage at which they first lose a required skill. The skill is not among the 50 candidates from retrieval, which applies only to the retrieval baselines, or it is dropped from the shortlist or at reranking. The gray remainder, labeled with its value, holds the queries with all required skills selected and equals FC@5. Most failed queries lose a required skill before reranking.
Missing required skills (% of the 200 Vanilla errors) ↓
Components
Substitution
Crowding
Diff.
Excl.
Name
FC@5 ↑
All
Similar
Same name
Desc.
Scope
Name
All
Duplicate
Generic
Others
Total
36.4
46.0
28.5
19.0
9.5
2.0
6.0
41.5
18.0
23.5
12.5
100.0
✓
53.5 +17.2
19.0 − 27.0
8.0
7.0
2.5
5.0
3.5
31.0 − 10.5
15.0
16.0
9.5 − 3.0
59.5
✓
49.5 +13.1
39.0 − 7.0
19.5
15.0
8.0
3.0
8.5
27.5 − 14.0
10.0
17.5
10.5 − 2.0
77.0
✓
42.9 +6.6
31.5 − 14.5
12.0
6.0
8.0
3.5
8.0
35.5 − 6.0
16.5
19.0
10.0 − 2.5
77.0
Appendix
Table A3: This table routes all eight combinations of the three components at S9 with Claude Haiku 4.5, to show how they interact. A check mark turns a component on, so the first row is Vanilla and the shaded row is Skill++ . The error columns count the missing required skills by the forms and types of Fig. 5 , as a share of the 200 Vanilla errors. Gray numbers give the change from Vanilla in points. Bold marks the best value per column and underline the second. Diff.: description differentiation. Excl.: scope exclusions. Name: name clarification, or Name Confusion among the error types. Desc.: Description Inconsistency. Same name: Similar-Skill Confusion errors in which the incoming skill has the name of the required skill. All configurations reuse the frozen outputs of Skill++ , and the exclusions-only row appends its clause to the original description.
Approach
FC@5 (%) ↑
S1
S2
S3
S4
S5
S6
S7
S8
S9
Avg
Router GPT-5.4-mini
Vanilla
87.5
78.3
76.2
68.0
72.5
67.9
61.3
62.6
59.6
70.4
Neighbor-contrastive
85.0
75.0
75.0
62.0
62.5
57.9
56.9
54.7
57.6
65.2
R&R
92.5
80.0
75.0
62.0
66.7
55.0
59.4
59.2
52.0
66.9
R&R-CFT
94.2
82.8
82.9
70.0
69.2
66.0
67.3
66.9
65.2
73.8
Appendix
Table A4: This table reports FC@5 (%) of the four other routers at every checkpoint and their mean over S1–S9 (Avg), to test whether the results of the main router hold. Each router routes the approaches of Tab. A1 except Body-distilled and CC-Pages, on the same inputs. -CFT results average three training seeds. Bold marks the best value per column within each router, and underline the second. At S9, Skill++ exceeds the strongest other approach in this table by 21.7, 13.6, 7.1 and 7.4 pp with GPT-5.4-mini, GPT-5.6 Luna, GPT-5.6 Sol and Qwen3.7-Flash.
Approach
Recall@5 (%) ↑
S1
S2
S3
S4
S5
S6
S7
S8
S9
Avg
Router GPT-5.4-mini
Vanilla
95.6
92.8
92.1
86.8
89.6
86.5
83.7
84.3
82.1
88.2
Neighbor-contrastive
94.2
91.1
90.4
82.9
84.3
81.4
81.0
79.5
80.6
85.0
R&R
97.7
92.2
91.6
85.4
87.0
82.8
85.2
82.8
81.2
87.3
R&R-CFT
98.3
94.3
94.1
88.8
88.4
86.9
88.0
87.6
86.5
90.3
Appendix
Table A5: This table reports Recall@5 (%) of the four other routers at every checkpoint and its mean over S1–S9 (Avg), to show how many required skills each approach keeps with other routers. The routing runs are those of Tab. A4 , and -CFT results average three training seeds. Bold marks the best value per column within each router, and underline the second.
Approach
FC@5 (%) ↑
Δ at S9
S1
S2
S3
S4
S5
S6
S7
S8
S9
Avg
SkillRet
Vanilla
88.9
75.9
59.7
50.0
35.2
29.4
20.8
16.7
15.6
43.6
Skill++ (ours)
91.7
90.7
70.8
65.6
45.4
38.9
30.6
27.2
30.0
54.5
+14.4
SkillRouter
Vanilla
80.1
64.6
52.4
43.3
29.6
31.2
23.4
29.0
19.8
41.5
Appendix
Table A6: This table reports FC@5 (%) at every session on SkillRet and SkillRouter, to test whether the gains hold on other benchmarks as their libraries grow to about 2,000 skills. Values are means over three addition orders, with Claude Haiku 4.5 as the router. Bold marks the better value per column. Δ : Skill++ minus Vanilla.
Figure A3: This figure shows FC@5 at every session in Codex CLI with GPT-5.6 Luna and GPT-5.6 Sol, to test whether the gains reach an agent harness as the library grows (values in Tab. A7 ). Skill++ stays above Vanilla at every session with both models.
Approach
FC@5 (%) ↑
Δ at S9
S1
S2
S3
S4
S5
S6
S7
S8
S9
Avg
Codex CLI, GPT-5.6 Luna
Vanilla
47.5
31.7
23.8
15.0
19.2
13.6
15.0
12.3
7.6
20.6
Skill++ (ours)
82.5
75.0
68.8
53.0
53.3
44.3
41.2
35.8
39.9
54.9
+32.3
Codex CLI, GPT-5.6 Sol
Vanilla
85.0
70.0
72.5
68.0
65.8
69.3
65.0
68.2
70.7
70.5
Appendix
Table A7: This table reports FC@5 (%) at every session in Codex CLI with GPT-5.6 Luna and GPT-5.6 Sol, to test whether the gains reach an agent harness as the library grows. FC@5 scores the first five skills that the agent names for the queries released so far, on the libraries of Tab. A2 . Bold marks the better value per column. Δ : Skill++ minus Vanilla.
Protocol change
FC@5 (%) ↑
Δ (pp)
Before
After
Display order shuffled
85.9
86.9
+1.0
Identical inputs repeated
85.9
84.8
− 1.0
Addition order permuted
82.3
79.3
− 3.0
Appendix
Table A8: This table reruns Skill++ at S9 with GPT-5.6 Luna under three protocol changes and reports FC@5 before and after each change. Δ : After minus Before. Every change shifts FC@5 by at most 3.0 pp, so routing noise stays small.
Reusable skills let LLM agents package task-specific procedures, tool affordances, and execution guidance into modular building blocks. As skill ecosystems grow to tens of thousands of entries, exposing every skill at inference time becomes infeasible. This creates a skill-routing problem: given a user task, the system must identify relevant skills before downstream planning or execution. Existing agent stacks often rely on progressive disclosure, exposing only skill names and descriptions while hiding the full implementation body. We examine this design choice on a SkillsBench-derived benchmark with approximately 80K candidate skills, targeting the practically important setting of large skill registries with heavy overlap. Across representative dense and reranking baselines on this setting, hiding the skill body causes a 37-44 percentage point drop in routing accuracy. Stronger controls show that the missing signal is body-resident rather than a simple length artifact: body-distilled descriptions recover part of the gap, but remain 7-21 points below direct all-field routing, while a metadata-only encoder trained with the same data remains 14.0 points below its all-field counterpart. Motivated by this finding, we present Skillrouter, a compact 1.2B body-aware retrieve-and-rerank pipeline. Skillrouter achieves 74.0% Hit@1 on our benchmark -- the strongest average top-1 routing performance among the baselines we evaluate -- while using 13× fewer parameters and running 5.8× faster than the strongest base pipeline. The ranking gains further generalize to a supplementary benchmark independently constructed from three skill sources. In a complementary end-to-end study across four coding agents, routing gains transfer to improved task success, with larger gains for more capable agents.
Large language model (LLM) agents increasingly rely on external skills, but routing user requests over large skill registries is difficult because many skills are functionally redundant while complex tasks often require complementary skill sets. Existing skill routers typically rank candidates independently by query relevance, which can waste context budget on redundant skills. We propose Diverse Skill Routing (DSR), a diversity-aware reranking framework that uses a Determinantal Point Process to balance relevance and non-redundancy. DSR introduces a query-residual diversity kernel that penalizes redundant skill overlap while reducing penalties caused only by shared query relevance. On the SkillRouter benchmark, DSR improves recall and full coverage over a strong pointwise reranking baseline, with larger gains on multi-skill queries. These results suggest that skill routing should be treated not only as relevance ranking, but also as complementary set selection.
Wang Wei, Tiankai Yang, Samyadeep Basu +7
Virginia Tech · University of Southern California · Adobe Research +3
Large language model (LLM) agents use external skills to reuse task procedures and experience with tools. General-purpose skills describe shared execution procedures, while specific tool choices, operating practices, and output requirements vary across users. In long-horizon tasks, subgoals, available inputs, and environmental states change as execution progresses. Agents must select currently applicable skills from an expanding skill pool and prepare candidates for subsequent steps. We propose Skill Adapter, which enables personalized modification and online routing of general-purpose skills. The system distills local adjustments from user requirements and execution feedback and stores them as Adapters linked to general-purpose skills. The routing agent selects general-purpose skills and applicable Adapters based on the current subtask, execution progress, and environmental feedback, incrementally maintaining a task-level online skill library that the main LLM reads on demand. The system preloads candidates for subsequent nodes and rechecks their applicability once actual inputs are determined. Reinforcement learning optimizes the two types of decisions using modification gains and routing outcomes, respectively. We evaluate Skill Adapter on ALFWorld, WebShop, and SkillsBench. Compared with SkillRL, it improves task success rates by an average of 11.43 percentage points and reduces mean execution time on all three benchmarks. Skill Adapter retains its performance advantage when the skill pool grows to 1,000 skills.