MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution

Zhiwei Shang; Yu Huo; Mingrong Gong; An Yan; Zikun Qu; Junhao Dong; Bryan Kian Hsiang Low; Chenglin Wu

cs.AIOct 4, 2026

MESH-Harness: Self-Improving Agent Harnesses via Bandit-Guided Compositional Evolution

Authors: Zhiwei Shang, Yu Huo, Mingrong Gong, An Yan, Zikun Qu, Junhao Dong, Bryan Kian Hsiang Low, Chenglin Wu, +1 more

Organizations: The Chinese University of Hong Kong, Shenzhen · DeepWisdom · The Chinese University of Hong Kong · Nanyang Technological University · Fudan University · National University of Singapore

Abstract

An agent harness is the code that organizes context, maintains state, and coordinates tool calls for a language model. We study how to improve the harness under a limited evaluation budget while keeping model weights fixed. Our method, MESH-Harness, organizes each harness into functional modules with explicit role-specific interfaces, allowing alternative implementations of each module to be substituted and recombined. It uses shared module representations and full-covariance LinUCB to score candidate combinations based on predicted performance and exploration value. Mixed-start coordinate ascent selects complete configurations for evaluation without enumerating the combinatorial space. Validation traces then guide local code edits, and the resulting candidates are incorporated into fixed-capacity role-specific pools for subsequent recombination. On text tasks, retrieval-augmented mathematical reasoning, code generation, and interactive scientific tasks, MESH-Harness outperforms Meta-Harness by 5.70, 7.01, 2.00, and 5.00 points, respectively, under matched candidate-evaluation budgets. Iterative harness optimization improves MESH-Harness by 5.63-7.79 points over its first-round configurations. For the reported configurations, aggregate test-time cost is 44.2% lower than that of Meta-Harness, while total cost including search is 14.6% lower. These results show that combining module-level design reuse with feedback-driven compositional search can systematically improve agent harnesses while keeping overall optimization cost under control.

Figures & tables

Figure 1: Overview of MESH-Harness. (a) Each functional slot has a fixed interface and a pool of LLM-initialized implementations with cached embeddings . (b) Full-covariance LinUCB scores configurations with one implementation per slot , and mixed-start coordinate ascent selects a configuration for evaluation. (c) The selected harness is executed to obtain validation rewards and traces. (d) Trace diagnosis guides edits to implementations and fixed-capacity pool updates. Rewards update the bandit model ; new implementations join their respective pools for subsequent composition .

Figure 2: Test performance across four task domains. (a) Text macro-average, overall Math pass@1, LiveCodeBench solve rate under the fixed cap-8 protocol, and ScienceWorld mean progress score. (b) Unweighted mean of the four task scores. All scores are on a 0–100 scale, with higher values indicating better performance. MESH-Harness achieves the highest score on all four aggregate metrics.

Method	Text	Math	LiveCodeBench	ScienceWorld
SkillOpt	53.27	46.40	57.00	53.00
DGM-H	42.78	53.00	72.00	52.20
ADIAS	42.50	52.60	69.00	43.10
AHE	47.39	50.60	69.00	49.00
Meta-Harness	50.63	46.20	75.00	53.10
MESH-Harness	56.33	53.21	77.00	58.10

Table 1: Held-out test performance. All methods use 40 candidate evaluations; scores average three test runs. Text: dataset macro-average; Math: pooled pass@1; LiveCodeBench: cap-8 solve rate; ScienceWorld: mean progress. Scores use a 0–100 scale. Bold marks the column maximum;

\Delta

compares MESH-Harness with Meta-Harness.

Harness	Score
No memory	26.07
Few-shot (8)	41.00
Few-shot (32)	46.87
Few-shot (all)	50.00
ACE memory	50.00
MCE memory	48.93

Table 2: Text reference harnesses. Fixed Meta-Harness seeds appear above the divider; scores are macro-averages.

Harness	Score
No retrieval	23.20
Random few-shot	41.42
BM25	42.18
ACE	42.38
Meta-Harness	46.20
MESH-Harness	53.21

Table 3: Math reference harnesses. Fixed Meta-Harness seeds appear above the divider; scores are overall pass@1.

Figure 3: Final performance relative to method-specific references. “Initial” denotes a fixed reference seed for Meta-Harness and the first evaluated composition for MESH-Harness, not a shared initialization. Meta-Harness references are 50.00 (Text), 42.38 (Math, ACE), 71.00 (LiveCodeBench), and 55.50 (ScienceWorld). Brackets show final minus reference.

Figure 4: Exploration strength. Text macro-average versus $\alpha$ ; the star marks the default. Reference lines show Meta-Harness and random selection.

Selection	Score	$\Delta$
No UCB bonus ( $\alpha=0$ )	51.70	$-4.63$
$\alpha=0.2$	53.17	$-3.16$
$\alpha=0.4$	54.87	$-1.46$
Full ( $\alpha=0.8$ )	56.33	0.00
$\alpha=1.6$	55.10	$-1.23$
Random composition	48.80	$-7.53$

Table 4: Configuration selection. Text macro-average;

\Delta

is relative to full MESH-Harness. Rows follow the

\alpha

sweep at left.

Variant	Score	$\Delta$
MESH-Harness	56.33	0.00
No pool refresh	51.20	$-5.13$
Refresh without historical traces	53.80	$-2.53$
Meta-Harness	50.63	$-5.70$

Table 5: Module evolution. Text macro-average over three test runs and change from the full method.

	Search + test			Test only
Task	Meta	MESH	Saving	Meta	MESH	Saving
Text	63.1843	51.1643	19.0%	0.1709	0.1662	2.8%
Math	58.8652	47.2431	19.7%	0.5475	0.4987	8.9%
LiveCodeBench	37.1387	34.7826	6.3%	0.5273	0.3847	27.0%
ScienceWorld	35.8655	33.4178	6.8%	2.3071	0.9339	59.5%
Total	195.0537	166.6078	14.6%	3.5528	1.9835	44.2%

Table 6: Search and execution costs (USD). Search + test includes optimization and testing the selected configurations; test only excludes optimization. Savings are relative to Meta-Harness. Totals sum the four reported task workloads.

Figure 5: Score–cost tradeoff. Circles: MESH-Harness; squares: Meta-Harness. The dashed line connects nondominated evaluated configurations. Cost uses a log scale.

	Score $\uparrow$		Cost $\downarrow$
Execution model	Meta	MESH	Meta	MESH
DeepSeek V4 Flash	50.63	56.33	0.1709	0.1662
GPT-5.6 Luna	51.00	55.37	0.5359	0.4987
Qwen 3.8 Flash	49.17	53.70	0.2608	0.2496
Claude Sonnet 5	55.57	59.93	7.4215	6.8874

Table 7: Frozen-harness transfer. Text macro-average and execution cost (USD), without further search. Bold marks the better result within each model.

Dataset	Meta-Harness solution	+ MESH refinement
LawBench	51.00	55.00
Symptom-to-Diagnosis	84.90	90.10
USPTO	16.00	18.00
Macro-average	50.63	54.37

Table 8: Refining a Meta-Harness solution. Held-out text scores before and after 20 additional MESH-Harness candidate evaluations.

Appendix figures & tables3 assets

Supplementary material from the paper’s appendix.

Appendix

Dataset	Train	Validation	Test	Prediction or interaction unit
USPTO	50	30	100	Precursor strings for a product molecule
Symptom-to-Diagnosis	200	50	212	A diagnosis from a symptom description
LawBench	200	50	100	A set of charges from a case description
Mathematical reasoning	–	400	500	A final mathematical answer
LiveCodeBench	100	100	100	One selected Python program per problem
ScienceWorld	66	22	102	One interactive episode

Appendix

Table 9: Task splits and prediction units. A dash indicates no separate training split. Math contains 200 validation problems from each source; its 500 test problems comprise 254 from OlympiadBench and 246 from MathArena. ScienceWorld counts are episodes.

Retrieval source	Problem–solution pairs
NuminaMath	55,968
Omni-MATH	3,201
DeepMath	98,670
OpenMathReasoning	267,647
PolyMath	8,440
Total	433,926

Appendix

Table 10: Math retrieval corpus after evaluation-overlap filtering and deduplication.

Setting	Value
Candidate-evaluation budget	40
Implementations per slot	10
Feature dimensions	$d=128$ per slot; $p=896$ for seven slots, $p=640$ for five
Ridge regularization; UCB coefficient	$\lambda=1$ ; $\alpha=0.8$
Coverage; family-reuse penalty	$\eta=0.04$ ; $\gamma=0.04$
Similarity attenuation; minimum scale	$\beta=0.25$ ; $g_{\min}=0.5$

Appendix

Table 11: Default search settings. The window

W

and refresh interval are measured in completed candidate evaluations.

Explore similar work

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry
Jun 12, 2026Tingyang Chen, Shuo Lu, Kang Zhao +11Agent Harness Multi-Agent Evolution
Darwin Agent Team
HARBOR: Automated Harness Optimization
Apr 22, 2026Biswa Sengupta, Jinhua WangAgent Harness Agentic Optimization
LLM Suite Team, JP Morgan Chase & Co.
HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses
Aug 3, 2026Luan Zhang, Ruochen Zhou, Dandan Song +9Evolving Harness Agent Harness
Beijing Institute of Technology, China · City University of Hong Kong, China · Independent, China

Jun 12, 2026, cs.AIJ/K move · Enter open · S save

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

Tingyang Chen, Shuo Lu, Kang Zhao, Weicheng Meng+10

Darwin Agent Team

Agent Harness Multi-Agent Evolution

Open paper AskPDF arXiv

AI agent performance depends critically on the runtime harness, comprising the prompts, tools, memory, and control flow that mediate how a model observes, reasons, and acts. Yet today's harnesses remain largely hand-crafted and static: each new model or task still demands bespoke scaffolding, and the rich traces produced during execution are rarely distilled back into systematic improvement. We introduce HarnessX, a foundry for composable, adaptive, and evolvable agent harnesses. HarnessX assembles typed harness primitives via a substitution algebra, adapts them through AEGIS, a trace-driven multi-agent evolution engine grounded in an operational mirror between symbolic adaptation and reinforcement learning, and closes the harness-model loop by turning trajectories into both harness updates and model training signal. Across five benchmarks (ALFWorld, GAIA, WebShop, tau^3-Bench, and SWE-bench Verified), HarnessX yields an average gain of +14.5% (up to +44.0%), with gains largest where baselines are lowest. These results suggest that agent progress need not come from model scaling alone: composing and evolving runtime interfaces from execution feedback is an actionable and complementary lever. The complete codebase will be open-sourced in a future release.

Abstract

Explore similar work

HarnessX: A Composable, Adaptive, and Evolvable Agent Harness Foundry

HARBOR: Automated Harness Optimization

HarnessCompass: Guiding Automatic Harness Evolution toward Generalizable and Effective Agent Harnesses