SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills

Enze Ma; Chunyu Miao; Yankai Chen; Jie Yang; Liancheng Fang; Kening Zheng; Hanrong Zhang; Muyao Xu

cs.AIOct 14, 2026

SkillNEO: Non-Elitist Evolutionary Optimization of Agent Skills

Authors: Enze Ma, Chunyu Miao, Yankai Chen, Jie Yang, Liancheng Fang, Kening Zheng, Hanrong Zhang, Muyao Xu,

Organizations: University of Illinois at Chicago · Mohamed bin Zayed University of Artiﬁcial Intelligence · Independent Researcher · University of California, San Diego ·

Abstract

Agent skills turn procedural knowledge into reusable artifacts, allowing LLM agents to accumulate and refine expertise through experience. Building on this, skill evolution iteratively improves skills using execution feedback. However, improvement may require several interdependent edits, so low-reward versions can still be worth developing. Requiring immediate reward gains can discard useful partial repairs before their benefits emerge. Non-elitist evolution allows new versions to receive further edits despite scoring below earlier ones. For agent skills, this calls for evidence of what to preserve and repair next. We introduce SkillNEO (Non-Elitist Evolutionary Optimization for Agent Skills), which separately selects a version to use and versions to keep improving. Comparing how related versions perform the same task reveals working steps to preserve and remaining failures to fix. It can also revisit and revise earlier versions using later evidence. Across 86 SkillsBench tasks in eight domains, including software engineering and office work, SkillNEO raises GPT-5.4 Mini's average reward from 49.1% to 66.4%, within GPT-5.5 and GPT-5.6 Luna's original-skill range. Mini executes tasks, proposes revisions, and edits skills; final evaluation uses the same task instances. Gains span all eight domains. The same skills improve stronger models without further editing. On the 41 tasks with modified skills, reuse improves Luna by 10.5 percentage points and places GPT-5.5 10.6 points above its published original-skill reference. Execution records show these skills can benefit stronger models even when Mini still fails some task requirements. Search histories also show lower-scoring versions leading to skills ultimately selected for use. Together, these findings show that skill evolution can turn a weaker model's partial progress into reusable procedural knowledge for improving more capable agents.

Figures & tables

Figure 1: Non-elitist evolution allows weaker revisions to lead to better skills. (a) Single-direction refinement discards alternative revisions, potentially losing useful partial repairs. (b) SkillNEO develops and revisits such revisions, using execution-trace comparisons to guide further repairs that can yield a new best skill. States

s_{i}

pair skill bundles with their execution records. The dark-blue node marks the new deployment incumbent; crossed-out nodes in (a) denote discarded revisions. Solid tree edges denote edits; in (b), the dashed orange arrow denotes reselection.

Figure 2: SkillNEO separates choosing a skill to use from choosing versions to improve. A version can receive further edits (green) even when it scores below the version selected for use (blue). To guide these edits, the Proposer compares saved task executions to identify steps that work and failures that need repair. The Skill Editor applies the proposed changes to instructions, scripts, and resources. Edit Validation checks the revised files before the Executor runs the task with the new version. The resulting scores inform selection, and execution records guide the next round. Mini fills every model-based role in our experiments.

Model	Original / reference	Final	$\Delta$ (pp)
GPT-5.4 Mini	49.1	66.4	+17.3
GPT-5.5	66.1	69.6	+3.5
GPT-5.6 Luna	67.3	71.9	+4.6
GPT-5.4 †	51.7	65.5	+13.8 †

Table 1: Overall rewards and cross-model reuse. Average task reward (%) for the 86-task assignment (a) and 41 modified tasks (b);

\Delta

is in percentage points.

\dagger

GPT-5.4 compares Vals (87 tasks, OpenHands) with final evaluation on 86 tasks using Codex. GPT-5.5 uses published, task-aligned SkillsBench references; Luna uses post-freeze evaluations of both conditions. Subset gains / ties / losses are 29/12/0 (Mini), 15/18/8 (GPT-5.5), and 11/23/7 (Luna), with ties within

\pm 0.05

pp.

Domain	$N$	No skill †	Original skills	SkillNEO	$\Delta$ (pp)
Software engineering	16	26.9	48.3	75.7	+27.4
Office / white collar	14	40.5	47.6	61.9	+14.3
Natural science	14	38.3	53.0	71.4	+18.4
Industrial / physical	14	28.6	48.3	53.9	+5.6
Finance / economics	9	18.5	22.2	48.1	+25.9
Mathematics / formal	7	38.1	61.9	79.5	+17.6

Table 2: Mini’s rewards across eight domains. Average task reward (%) on the same 86 tasks. No skill † is a published GPT-5.4 Mini/OpenHands reference , reaggregated by domain; Original skills and SkillNEO use our Mini/Codex high evaluation.

\Delta=\text{\mbox{SkillNEO}}-\text{Original skills}

, in percentage points. The Overall row averages all 86 tasks.

Figure 3: Mini improves across all eight domains. No skill † uses the OpenHands reference in Table 2 ; Original skills and SkillNEO use our Mini/Codex high evaluation. Parenthesized gains are SkillNEO minus Original skills (pp). Domain counts sum to 86.

Figure 4: Case studies of skill evolution in SkillNEO. (a) A zero-reward partial repair leads to the next selected skill in Gravitational Wave Detection. (b) Sales Pivot Analysis reuses a sibling’s PDF extraction procedure in another branch. (c) Revisiting an earlier parent produces the final skill in Paratransit. (d) Restarting from the original bundle uses execution evidence collected later in Wyckoff. Panel (a) reports three-run mean rewards at creation. In (c) and (d), solid edges show primary parents, broken arrows show reuse or reselection, and rewards come from independent final Mini evaluations (Appendices H and I ).

Model	Reward	Intended scan scope	Correct output fields
Mini	66.7	3/3	2/3
GPT-5.4	100.0	3/3	3/3
GPT-5.5	100.0	3/3	3/3
Luna	100.0	3/3	3/3

Table 3: Execution behavior with the same final skill bundle. Models differ in which requirements they satisfy despite receiving identical guidance. Counts give passes out of three executions; skipped checks are not passes. For Sales Pivot, Valid pivot objects requires the row-field, aggregation, and cache-field checks to pass. Reward is mean task reward (%).

Appendix figures & tables14 assets

Supplementary material from the paper’s appendix.

Appendix

Model / agent	No skill	Original skill	$\Delta$
Mini / OpenHands (official)	29.9	40.7	+10.8
Mini / Codex high (this study)	39.1	49.1	+10.0
GPT-5.5 / OpenHands (official)	50.9	66.9	+16.0
GPT-5.5 / Codex (official)	46.2	66.1	+19.9

Appendix

Table 4: No-skill and original-skill references. Original skills increase average reward in each listed configuration on the aligned 86 tasks. Rewards are percentages and

\Delta

is in percentage points. Official rows are reaggregated from the published per-task registry. Differences are computed from the displayed means. No Luna no-skill result has been measured.

Study	Executor	Tasks	Human	Developed
SkillAudit ( Gao et al., 2026 )	Opus 4.8	89	56.7	73.9
MUSE-Autoskill ( Lin et al., 2026a )	GPT-5.5	75	59.67	53.42
SPARK ( Zhou et al., 2026b )	GPT-5.4 Mini	86	$\approx 47$	$\approx 52$
SkillNEO (this study)	GPT-5.4 Mini	86	49.1	66.4

Appendix

Table 5: Reported skill-development results on SkillsBench. Average rewards (%) use each study’s task cohort and evaluation protocol. Human denotes each study’s human-skill reference; Developed uses its resulting skills. SkillEvolver and CoEvoSkills instead report complete-pass frequencies. SkillAudit, MUSE-Autoskill, and SkillNEO use the listed model for development and execution; SPARK uses stronger-model teacher trajectories; SPARK’s scores follow Section 4.1 of the source. SkillAudit and SkillNEO refine supplied skills; MUSE-Autoskill and SPARK generate skills, with Human as a separate reference. MUSE counts its 28 uncovered tasks as zero. SPARK describes an 86-task suite; exact Mini task alignment is unavailable. For SkillNEO , 41 modified bundles receive new final executions; 45 retained bundles share their original Mini measurements.

		GPT-5.4	GPT-5.5			GPT-5.6 Luna
Mini outcome	$n$	Evolved	Original	Evolved	Gap	Original	Evolved	Gap
All modified	41	66.8	60.5	71.1	+10.6	63.9	74.4	+10.5
Mini improved	29	69.1	64.3	78.1	+13.8	62.8	81.0	+18.3
Mini tied	12	61.1	51.4	54.2	+2.8	66.7	58.3	-8.3

Appendix

Table 6: Receiver rewards grouped by Mini’s outcome. GPT-5.5 and Luna have larger mean gains on tasks where Mini improves than on tasks where Mini ties. Scores report average reward (%); Gap is evolved minus original reward in percentage points. The 41 modified tasks are grouped post hoc by Mini’s final evaluation outcomes, using its

\pm 0.05

pp display band. Evolved denotes the same frozen Mini-developed bundle for each task. GPT-5.4 reports frozen-skill endpoints; original-skill subgroup scores are not reported. Evaluation settings follow Section 4.1 .

GPT-5.5 direction	Luna gain	Luna tie	Luna loss	Total
Gain	6	6	3	15
Tie	4	13	1	18
Loss	1	4	3	8
Total	11	23	7	41

Appendix

Table 7: Joint directions of receiver reward changes. Gains and losses need not coincide across GPT-5.5 and Luna on the 41 modified tasks. Rows use GPT-5.5 reference differences; columns use Luna differences from post-freeze evaluations. Both axes use the existing

\pm 0.05

pp display band. Original-skill reference sources appear in Appendix B .

Stratum	$n$	Original	Evolved	$\Delta$	Full-set contribution
Modified skills	41	63.9	74.4	+10.5	+5.0
Mini positive subset	29	62.8	81.0	+18.3	+6.2
Mini tied subset	12	66.7	58.3	-8.3	-1.2
Original retained	45	70.4	69.6	-0.7	-0.4

Appendix

Table 8: Contributions to Luna’s overall reward difference. Gains on modified tasks outweigh the decrease on retained tasks. Rewards are percentages;

\Delta

and Full-set contribution are in percentage points. The Mini-positive and Mini-tied subsets partition the 41 modified tasks. The 41 modified and 45 retained tasks partition the benchmark. Their contributions are

n\Delta/86

and sum using unrounded values. Mini-positive/tied strata are defined post hoc from Mini’s final evaluation outcomes.

Original-performance stratum	$n$	Original	Evolved	$\Delta$	G/T/L
Zero observed reward	8	0.0	50.0	+50.0	4/4/0
Partial observed reward	16	57.5	61.4	+3.9	7/3/6
Perfect observed reward	17	100.0	98.0	-2.0	0/16/1

Appendix

Table 9: Luna transfer by observed original performance. Among the 41 modified tasks, the group with zero original reward has the largest mean gain. Rewards are percentages,

\Delta

is in percentage points, and G/T/L counts gains, ties, and losses with the

\pm 0.05

pp display tolerance of Table 1 . Groups are defined post hoc from Luna’s three original-skill repeats.

Domain	All	Modified	Mini mod.	Luna mod.	Luna all
Cybersecurity	7	4	+22.2	+44.4	+25.4
Finance / economics	9	4	+58.3	+25.0	+3.7
Industrial / physical	14	7	+11.3	-11.9	-10.7
Mathematics / formal	7	3	+41.1	-10.6	+0.2
Media / content	5	2	+33.3	+0.0	+13.3
Natural science	14	6	+42.9	+11.1	+9.5

Appendix

Table 10: Domain-level improvement and transfer. Mini improves in every domain, while Luna differences vary by domain. Differences are percentage points. All and Modified give task counts; the modified-task and full-domain differences use their respective denominators.

Task		Mini O	Mini E	5.5 O	5.5 E	Luna O	Luna E
3d-scan-calc	R	100.0	100.0	100.0	100.0	100.0	100.0
ada-bathroom-plan-repair	R	33.3	33.3	100.0	100.0	100.0	100.0
adaptive-cruise-control	M	33.3	66.7	33.3	100.0	66.7	100.0
azure-bgp-oscillation-route-leak	R	0.0	0.0	0.0	0.0	0.0	0.0
citation-check	R	100.0	100.0	100.0	100.0	100.0	100.0
civ6-adjacency-optimizer	M	0.0	23.3	95.0	63.3	63.3	31.7

Appendix

Table 11: Complete task-level rewards. Each row reports mean reward (%) on one of the 86 tasks. M denotes modified bundles; R denotes byte-identical retained bundles. O/E denote original/final assignments. Mini’s R rows reuse the same original three-run score in both columns. Evaluation follows Section 4.1 ; Appendix B identifies the sources of the original-skill references.

Task	Original	Evolved	Change (pp)
Energy Market Pricing	66.7	0.0	$-66.7$
Grid Dispatch Operator	66.7	0.0	$-66.7$
Organize Messy Files	66.7	0.0	$-66.7$
Civ6 Adjacency Optimizer	63.3	31.7	$-31.7$
Drone Planning Control	84.4	67.8	$-16.7$
JPG OCR Statistics	33.3	0.0	$-33.3$

Appendix

Table 12: Luna tasks with observed transfer losses. Seven modified tasks lose reward under evolved bundles. Values are mean rewards (%); Change (pp) uses unrounded measurements.

Property	Value
Tasks with changed skill bundles	41/86 (47.7%)
Skill packages changed (counted per task)	62/228 (27.2%)
Total lines: original $\to$ deployed	106,632 $\to$ 108,233 (+1.5%)
Inserted + deleted lines: total / mean / median	8,147 / 198.7 / 157
Mean net line change per task: SKILL.md	-35.0
Mean net line change per task: support scripts	+74.0

Appendix

Table 13: Changes from original to deployed skill bundles. Core instructions become shorter on average while support scripts grow. The first two rows cover all 86 tasks; remaining statistics use the 41 modified tasks. Means and medians are per task. Packages and files are counted separately for each task; 228 counts the union of original and deployed packages. Line edits = insertions + deletions; net change = insertions

-

deletions.

\rho

is Spearman correlation.

Task	Generation	Retained parent	Higher-scoring saved versions
Gravitational Wave	4	e04 : 0.0	e01 : 66.7; d01 , b07 : 33.3
Data-to-D3	3	d03 : 33.3	c01 , c02 , b02 : 66.7

Appendix

Table 14: Parent eligibility beyond the historical top three. Both searches retain a parent despite three higher-scoring saved versions. Scores give each version’s latest complete three-execution mean (%) at that generation. Independent final Mini evaluation gives both tasks 100.0, up from 0.0.

Adopted lineage depth	Tasks
1	6
2	13
3	5
4	6
5	11

Appendix

Table 15: Adopted lineage depth. The 41 adopted lineages have mean depth 3.07 and median depth three. Depth counts primary-parent edits from the recorded root to deployment. It can be smaller than the generation number when a search revisits an earlier node.

Operator	Candidates	Edits on final paths	Final edits
consolidate	60	2	2
create	12	3	2
distill a	129	13	7
drop	5	0	0
extend	244	39	7
graft	64	8	3

Appendix

Table 16: Recorded edit operators. Counts cover the 41 experiment trees that produced adopted non-root skills. Candidates counts retained candidate versions, Edits on final paths counts adopted ancestry edges, and Final edits counts the 41 edges producing the final deployed bundles. These frequencies do not measure operator success rates. The 971 candidate records and 126 edits on final paths all record Mini as both diagnosis and writing model.

Task	Revision illustrated	Mini	Luna
Software dependency audit	Compare executions; refine report checks, then scan scope	$0.0\to 66.7$	$0.0\to 100.0$
PDDL airport planning	Complete a missing helper; strengthen saved-plan checks	$33.3\to 100.0$	$100.0\to 100.0$
Sales pivot analysis	Graft PDF extraction from a non-deployed sibling	$0.0\to 33.3$	$0.0\to 100.0$
Gravitational wave detection	Consolidate a non-deployed branch’s conditioning and search workflow	$0.0\to 100.0$	$100.0\to 100.0$

Appendix

Table 17: Skill-revision cases and final bundle performance. Scores show original

\to

evolved reward (%) for complete bundles. These cases illustrate recorded revisions; the scores do not isolate individual edit effects. Evaluation settings follow Section 4.1 .

LLM Agent Skill Learning

Large language model agent skill learning studies how agents acquire, represent, reuse, and refine procedures for multi-step tasks.

See all 380 papers

SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization
Sep 30, 2026Huancheng Chen, Xiaodi Sun, Zhaoqiong Huang +3LLM Agent Self-Improvement LLM Agent Skill Learning
Microsoft AI
SkillFocus: Evolving Agent Skills via Capability Decomposition
Sep 28, 2026Ning Wang, Zhiren Gong, Bingdong Li +2LLM Agent Skill Learning Task Decomposition
East China Normal University · Nanyang Technological University · Southern University of Science and Technology +1
SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision
May 31, 2026Yuxuan Liu, Zhaochen Su, Lingyun Xie +11LLM Agent Self-Improvement LLM Agent Skill Learning
The Hong Kong University of Science and Technology · Harbin Institute of Technology · Harbin Institute of Technology, Shenzhen +2

Sep 30, 2026J/K move · Enter open · S save

SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization

Huancheng Chen, Xiaodi Sun, Zhaoqiong Huang, Shenyang Huang+2

Microsoft AI

LLM Agent Self-Improvement LLM Agent Skill Learning

Open paper AskPDF arXiv

Natural-language skills are textual procedural memories through which large language model (LLM) agents retain reusable task knowledge without updating model weights. Existing methods typically treat skills as either static artifacts or monolithic documents optimized using aggregate validation scores as feedback. However, representing a skill as a monolithic document restricts optimization to its textual content, without explicitly modeling the structure through which procedural knowledge is retrieved and executed. We identify a key distinction between learning what knowledge to retain and determining how to organize it: textual updates should first be validated through execution evidence, after which the retained knowledge should be structured according to its procedural dependencies and retrieval requirements. To this end, we introduce SkillSpec, a two-phase framework comprising consensus-gated evolution and representation specialization. In the consensus-gated phase, complementary editing intents generate complete candidate skills. An update is committed only when paired evaluations reach consensus, requiring sufficient overall improvement and non-negative aggregate paired gain in every repeated evaluation. In the specialization phase, signals of process and redundancy sensitivity derived from the full optimization trajectory, including accepted and rejected candidates, guide the selection of a flat, graph, or hybrid representation.Across six benchmarks and three target language models, SkillSpec improves average success rate over SkillOpt by 6.89%, averaged across the three models. These results demonstrate that reliable skill evolution and representation specialization address complementary objectives: deciding what knowledge to retain and how to structure it for inference.

Abstract

LLM Agent Skill Learning

Explore similar work

SkillSpec: Consensus-Gated Agent Skill Evolution via Representation Specialization

SkillFocus: Evolving Agent Skills via Capability Decomposition

SkillRevise: Improving LLM-Authored Agent Skills via Trace-Conditioned Skill Revision