AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills

• URL: http://arxiv.org/abs/2606.29999v1
• Date: Mon, 29 Jun 2026 09:09:16 GMT
• Title: AlgoSkill: Learning to Design Algorithms by Scheduling Human-Like Skills
• Abstract summary: We propose AlgoSkill, which models algorithm design as sequential decision-making over a typed library of algorithmic skills.<n>A Monte Carlo Tree Search controller explores sequences using verification feedback from compilation, testing, stress testing, and complexity analysis.
• Score: 7.798940465229644
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Designing an algorithm from a natural-language problem statement requires identifying the problem structure, reading constraints, choosing a suitable paradigm, checking correctness, and refining complexity. Existing large language model (LLM) methods often rely on direct generation or generic self-refinement, leaving these steps implicit. We propose AlgoSkill, which models algorithm design as sequential decision-making over a typed library of algorithmic skills, including abstraction, constraint analysis, state design, data-structure selection, proof checking, counterexample construction, and complexity refinement. A learned scheduler proposes skills from the current design state, while a Monte Carlo Tree Search (MCTS) controller explores skill sequences using verification feedback from compilation, testing, stress testing, and complexity analysis. Experiments on competitive programming and combinatorial optimization benchmarks show that AlgoSkill improves over direct LLM generation, chain-of-thought prompting, self-refinement, and MCTS without typed skills. Ablations show that typed skills, verification-based repair, and search-based scheduling each contribute to performance. These results support treating automatic algorithm design as verification-guided skill scheduling rather than one-shot code generation.

Related papers

• AlgoBench: Benchmarking Algorithmic Adaptation in Code Generation [7.798940465229644]
  We introduce ALGOBENCH, a framework that automatically builds novel algorithmic problems from known competitive-programming problems.<n>We show that performance drops sharply on ALGOBENCH variants, retrieval can increase reuse of the old algorithm, and many correct-looking solutions fail to meet the required complexity.
  arXiv  Detail & Related papers  (2026-06-30T10:13:12Z)
• Budget-Efficient Automatic Algorithm Design via Code Graph [2.982218441172364]
  Large language models (LLMs) have emerged as powerful tools for automatic algorithm design (AAD)<n>We formalize budget-efficient automatic algorithm design, wherein the search policy maximizes realized fitness subject to limited computational cost.<n>We validate our method empirically on three optimization problems, demonstrating consistent superiority of our graph-based search over full-algorithm search at equal token budget.
  arXiv  Detail & Related papers  (2026-05-11T14:01:52Z)
• Evaluating Prompting and Execution-Based Methods for Deterministic Computation in LLMs [1.2957535240267326]
  Large Language Models (LLMs) have demonstrated strong capabilities in natural language understanding and reasoning.<n>We systematically evaluate multiple prompting strategies, including Chain-of-Thought (CoT), Least-to-Most decomposition, Program-of-Thought (PoT), and Self-Consistency (SC)<n>Our results show that standard prompting methods achieve only moderate accuracy on sequence-based tasks.
  arXiv  Detail & Related papers  (2026-05-04T23:32:37Z)
• Early Discoveries of Algorithmist I: Promise of Provable Algorithm Synthesis at Scale [9.349595533902479]
  Algorithmist is an autonomous researcher agent on top of GitHub Copilot.<n>We evaluate it on research-level tasks in private data analysis and clustering.<n>Results suggest a new paradigm in which LLM systems generate research-paper-quality algorithmic artifacts tailored to each dataset and deployment setting.
  arXiv  Detail & Related papers  (2026-03-23T04:06:55Z)
• Barbarians at the Gate: How AI is Upending Systems Research [58.95406995634148]
  We argue that systems research, long focused on designing and evaluating new performance-oriented algorithms, is particularly well-suited for AI-driven solution discovery.<n>We term this approach as AI-Driven Research for Systems ( ADRS), which iteratively generates, evaluates, and refines solutions.<n>Our results highlight both the disruptive potential and the urgent need to adapt systems research practices in the age of AI.
  arXiv  Detail & Related papers  (2025-10-07T17:49:24Z)
• Discovering Algorithms with Computational Language Processing [0.7062238472483737]
  We present a framework automating algorithm discovery by conceptualizing them as sequences of operations, represented as tokens.<n>These computational tokens are chained using a grammar, enabling the formation of increasingly sophisticated procedures.<n>Our ensemble Monte Carlo tree search (MCTS) guided by reinforcement learning (RL) explores token chaining and drives the creation of new tokens.
  arXiv  Detail & Related papers  (2025-07-03T21:45:17Z)
• PlanGEN: A Multi-Agent Framework for Generating Planning and Reasoning Trajectories for Complex Problem Solving [89.60370366013142]
  We propose PlanGEN, a model-agnostic and easily scalable agent framework with three key components: constraint, verification, and selection agents.<n>Specifically, our approach proposes constraint-guided iterative verification to enhance performance of inference-time algorithms.
  arXiv  Detail & Related papers  (2025-02-22T06:21:56Z)
• Designing Algorithms Empowered by Language Models: An Analytical Framework, Case Studies, and Insights [86.06371692309972]
  This work presents an analytical framework for the design and analysis of large language models (LLMs)-based algorithms.<n>Our proposed framework serves as an attempt to mitigate such headaches.
  arXiv  Detail & Related papers  (2024-07-20T07:39:07Z)
• Contractual Reinforcement Learning: Pulling Arms with Invisible Hands [68.77645200579181]
  We propose a theoretical framework for aligning economic interests of different stakeholders in the online learning problems through contract design. For the planning problem, we design an efficient dynamic programming algorithm to determine the optimal contracts against the far-sighted agent. For the learning problem, we introduce a generic design of no-regret learning algorithms to untangle the challenges from robust design of contracts to the balance of exploration and exploitation.
  arXiv  Detail & Related papers  (2024-07-01T16:53:00Z)
• When Do Program-of-Thoughts Work for Reasoning? [51.2699797837818]
  We propose complexity-impacted reasoning score (CIRS) to measure correlation between code and reasoning abilities. Specifically, we use the abstract syntax tree to encode the structural information and calculate logical complexity. Code will be integrated into the EasyInstruct framework at https://github.com/zjunlp/EasyInstruct.
  arXiv  Detail & Related papers  (2023-08-29T17:22:39Z)
• A Two-stage Framework and Reinforcement Learning-based Optimization Algorithms for Complex Scheduling Problems [54.61091936472494]
  We develop a two-stage framework, in which reinforcement learning (RL) and traditional operations research (OR) algorithms are combined together. The scheduling problem is solved in two stages, including a finite Markov decision process (MDP) and a mixed-integer programming process, respectively. Results show that the proposed algorithms could stably and efficiently obtain satisfactory scheduling schemes for agile Earth observation satellite scheduling problems.
  arXiv  Detail & Related papers  (2021-03-10T03:16:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.