Compiling a natural-language agent skill into model parameters removes the skill text from the prompt and leaves behind a small artifact that can be distributed and reused. Existing methods differ in where they inject the compiled quantity, and all of them assume that the artifact carries the content of the skill. We test that assumption. Through three controls on a retrieval agent, we find that a compiled skill shift carries a domain-general behavioural prior, not the content of the skill. A wrong skill document performs on par with the correct one, a single averaged bundle matches per-skill routing under a two-sided equivalence test, and a same-norm random direction collapses to the no-injection baseline, which shows that the trained direction stays load-bearing. We then introduce SKILL2STEER, a one-pass hypernetwork that reads a skill document once and maps it to low-rank activation shifts added at the output of every decoder block. Each skill compiles to 2.36M parameters, 9.25 times fewer than a weight-space adapter, while the base weights stay frozen and the generator runs only at compile time. The shift can be scheduled across retrieval steps and deployed as one routing-free bundle. On SearchQA, a seven-dataset benchmark, SKILL2STEER reaches 37.9 exact match, 9.8 points above the frozen model and 2.3 points above a weight-space method that ships 9.25 times more parameters per skill.
Figures & tables
Figure 2: Skill2Steer . A frozen encoder reads the skill document once, a hypernetwork emits one low-rank factor pair per decoder block, and the offset is added at each block output. The exported bundle mounts on the inference engine with no change to the base weights.
Exact match per dataset (%)
Summary
Method
NQ
TriviaQA
PopQA
Avg ↑
Δ Avg
Params / skill
Extra input
Prompting, retrieval
Vanilla (base)
25.2
50.6
35.2
37.0
ref.
—
✗
CoT
19.2
50.8
20.0
30.0
−7.0
—
✓
Few-Shot
34.6
57.6
39.4
43.9
+6.9
—
✓
R1-Instruct
27.0
55.0
31.6
37.9
+0.9
—
✓
Table 1: Single-hop retrieval QA, grouped by method family. Bold marks the best value in a column and underline the second best; ties share a mark. A shaded row marks the best method in each family. In the parameter column, bold marks the smallest shipped artifact, and prompt-based methods ship none. Δ Avg is the change in Avg with respect to Vanilla, and “Extra input” marks whether a method needs more than the question at inference.
Exact match per dataset (%)
Summary
Method
HotpotQA
2Wiki
MuSiQue
Bamboogle
Avg ↑
Δ Avg
Params / skill
Extra input
Prompting, retrieval
Vanilla (base)
26.2
26.8
4.2
28.8
21.5
ref.
—
✗
CoT
22.4
26.2
5.0
37.6
22.8
+1.3
—
✓
Few-Shot
30.0
25.8
6.0
17.6
19.9
−1.6
—
✓
R1-Instruct
26.6
33.6
5.8
34.4
25.1
+3.6
—
✓
Table 2: Multi-hop retrieval QA, grouped by method family. Bold marks the best value in a column and underline the second best; ties share a mark. A shaded row marks the best method in each family. In the parameter column, bold marks the smallest shipped artifact. The static and generation-only injection policies are reported in Table 6 . Δ Avg is the change in Avg with respect to Vanilla, ‡ marks sample-weighted averages, and “Extra input” marks whether a method needs more than the question at inference.
Method
1-hop
Multi
All-7
Params
Vanilla (base)
37.0
21.5
28.1
–
LatentSkill
44.9
27.0
35.6
21.8 M
Ours (static / static)
46.6
25.7
35.7
2.36 M
Ours (static / sched1)
46.6
30.0
37.9
2.36 M
Ours (6000 steps)
43.7
30.0
36.6
2.36 M
Ours (universal)
47.1
30.2
38.3
2.36 M
Table 3: All seven datasets, sample weighted. Every variant ships one small bundle, and the best one needs no routing.
Setting
EM
Steps
Inv.%
Chars
Single-hop (1500)
No injection
38.5
1.38
3.33
2238
Skill2Steer
46.6
2.15
0.03
45
Skill2Steer (sched1)
45.8
2.16
3.31
1411
Multi-hop (1625)
No injection
25.2
1.65
5.77
3287
Table 4: Behaviour of the compiled shift. The no-injection rows come from the same pipeline as the reported runs.
Appendix figures & tables1 asset
Supplementary material from the paper’s appendix.
Appendix
Setting
EM
Steps
Inv.%
Chars
Ours (6000 steps)
43.7
1.93
0.00
3132
Ours (gen-only, multi)
14.2
1.01
–
5108
Appendix
Table 8: Behaviour statistics for the longer-budget variants.
Agent systems increasingly use textual skills to encode reusable task procedures, but injecting these skills into the prompt at every step incurs substantial context overhead and exposes skill content as plaintext. We present LatentSkill, a framework that converts textual skills into plug-and-play LoRA adapters through a pretrained hypernetwork. LatentSkill stores skill knowledge in weight space rather than context space, removing per-step skill tokens while preserving modular loading, scaling, and composition. On ALFWorld and Search-QA, LatentSkill outperforms the corresponding in-context skill baseline while using substantially fewer prefill tokens: it improves ALFWorld success by 21.4 and 13.4 points on the seen and unseen splits with 64.1% fewer prefill tokens, and improves Search-QA exact match by 3.0 points with 72.2% lower skill-token overhead. Further analysis shows that generated skill LoRAs form a structured semantic geometry, can be precisely controlled via the LoRA scaling coefficient, and can be composed through parameter-space arithmetic when skill components are aligned. These findings suggest that weight-space skills provide an efficient, modular, and less exposed substrate for extending LLM agents.
Aofan Yu, Chenyu Zhou, Tianyi Xu +8
Shanghai Jiao Tong University · Sun Yat-Sen University · Shanghai Innovation Institute +1
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.
Skills extend an LLM agent beyond its parametric knowledge, and the gain they promise rests on picking the right one. Deployed harnesses route by preloading every skill's metadata into the context, which disperses the agent's attention and caps the library size. Retrieval pipelines move the selection out of the context, but also out of the agent's capability. We show that the frozen agent LLM already carries the routing signal in its own forward passes, and that two linear maps suffice to read it out with no skill text in the context. Our Gavel (Glance And Verdict from a frozen LLM) reads it in two steps. A glance scores the full library by matching the task's mid-layer states against a compact bank that one forward pass builds for each skill at installation, with the two maps as the only trained parameters. A verdict then resumes each shortlisted skill's forward pass, reads the model's own likelihood and yes/no judgment, and fuses both with the glance as a product of experts. Trained once, Gavel transfers zero-shot to three public benchmarks and SkillTraj, our new benchmark of 372 simulated agent trajectories. On Qwen3-32B it outperforms progressive disclosure and retrieve-and-rerank pipelines that add 1.2B to 16B external parameters, by up to 13.4 points on written tasks and up to 21.9 when the need for a skill arises mid-rollout. Routing accuracy improves as the backbone does, and in a bash-agent harness Gavel lets the 32B trigger the right skill on Skill-Use more often than models of up to 1.6T parameters in Codex.
Ruishuo Chen, Xun Wang, Yu Chen +2
Institute for Interdisciplinary Information Sciences, Tsinghua University