MOCHA: Multi-Objective Chebyshev Annealing for Agent Skill Optimization
arXiv cs.AI·Md Mehrab Tanjim, Jayakumar Subramanian, Xiang Chen, Branislav Kveton, Subhojyoti Mukherjee, Anlan Zhang, Sungchul Kim, Somdeb Sarkhel, Sunav Choudhury
17h agoQuick Take
MOCHA optimizes agent skills using multi-objective Chebyshev annealing for enhanced performance.
Key Points
- Skills are constrained by platform limits and require multi-objective optimization.
- MOCHA outperforms existing optimizers in diverse agent tasks.
- Achieved up to 14.9% improvement on specific tasks.
📖 Reader Mode
~2 min readAbstract:LLM agents organize behavior through skills - structured natural-language specifications governing how an agent reasons, retrieves, and responds. Unlike monolithic prompts, skills are multi-field artifacts subject to hard platform constraints: description fields are truncated for routing, instruction bodies are compacted via progressive disclosure, and co-resident skills compete for limited context windows. These constraints make skill optimization inherently multi-objective: a skill must simultaneously maximize task performance and satisfy platform limits. Yet existing prompt optimizers either ignore these trade-offs or collapse them into a weighted sum, missing Pareto-optimal variants in non-convex objective regions. We introduce MOCHA (Multi-Objective Chebyshev Annealing), which replaces single-objective selection with Chebyshev scalarization - covering the full Pareto front, including non-convex regions - combined with exponential annealing that transitions from exploration to exploitation. In our experiments across six diverse agent skills - where all methods share the same multi-objective mutation operator and baselines receive identical per-objective textual feedback - existing optimizers fail to improve the seed skill on 4 of 6 tasks: 1000 rollouts yield zero progress. MOCHA breaks through on every task, achieving 7.5% relative improvement in mean correctness over the strongest baseline (up to 14.9% on FEVER and 10.4% on TheoremQA) while discovering twice as many more Pareto-optimal skill variants.
| Comments: | Preprint. 25 pages, 14 figures, 5 tables |
| Subjects: | Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Software Engineering (cs.SE) |
| ACM classes: | I.2.7; I.2.6; I.2.4; I.2.8 |
| Cite as: | arXiv:2605.19330 [cs.AI] |
| (or arXiv:2605.19330v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2605.19330 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Md Mehrab Tanjim [view email]
[v1]
Tue, 19 May 2026 04:07:41 UTC (656 KB)
— Originally published at arxiv.org
More from arXiv cs.AI
See more →1d ago
FeaturedOriginal
From Prompts to Protocols: An AI Agent for Laboratory Automation
AI Summary
An AI agent integrates large language models for automating laboratory protocols, enhancing efficiency and accuracy.