ARES-LSHADE: Autoresearch-Enhanced LSHADE with Memetic Polish for the GNBG Benchmark

• URL: http://arxiv.org/abs/2605.13877v2
• Date: Sat, 16 May 2026 22:18:24 GMT
• Title: ARES-LSHADE: Autoresearch-Enhanced LSHADE with Memetic Polish for the GNBG Benchmark
• Abstract summary: We present ARES-LSHADE, a memetic differential-evolution variant submitted to the GECCO 2026 competition on LLM-designed evolutionary algorithms.<n>The algorithm builds on the LLM-LSHADE 2025 winner, contributing two new components.<n>The resulting algorithm trivially solved all 24 functions but violated the competition's blackbox rule.
• Score: 0.5186554442959231
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We present ARES-LSHADE, a memetic differential-evolution variant submitted to the GECCO 2026 competition on LLM-designed evolutionary algorithms for the Generalized Numerical Benchmark Generator (GNBG). The algorithm builds on the LLM-LSHADE 2025 winner, contributing two new components: (a) a scout-augmented mutation operator with adaptive CMA-ES integration, produced by an autonomous research loop across approximately thirty LLM-driven design experiments, and (b) a multi-start L-BFGS-B polish phase that respects strict blackbox treatment of the benchmark. On the official 31-run-per-function evaluation with the competition-specified function-evaluation budgets, ARES-LSHADE obtains 510 of 744 wins (per-function gap below 1e-8), reaching machine precision on 18 of 24 functions. The remaining six functions exhibit characteristic plateau signatures consistent with GNBG's compositional structure, and were independently identified by the autoresearch loop as the hardest of the suite. Beyond the result itself, this report documents two methodological observations: (i) an LLM-driven research loop with operator-only edit surface and fitness-only observation space converges to a characteristic plateau on this benchmark; (ii) when we initially widened the observation space to include the benchmark's compositional metadata, the resulting algorithm trivially solved all 24 functions but violated the competition's blackbox rule, which we identified before submission. We discuss this tension between LLM capability and benchmark integrity as a design consideration for future LLM-driven optimization-algorithm research. Code and reproducibility artifacts are available at https://github.com/anaeem1/ARES-LSHADE.

Related papers

• LLM-Driven Joint Evolution of Coupled Heuristics Components for Routing Optimization [6.642260387629958]
  This paper proposes a population-based framework that jointly generates and co-evolves interdependent components under a shared design blueprint.<n>Across synthetic instances and 41 public benchmarks, LLM-HCJG attains consistently low optimality gaps.
  arXiv  Detail & Related papers  (2026-09-02T09:25:55Z)
• Spicing up Genetic Netlist Generation with LLMs [6.183928830125183]
  We introduce LLM-SPICEMixer, a hybrid synthesis framework that augments genetic netlist generation with IGEL (Inspiration-Guided Evolution with LLMs)<n>During search, IGEL prompts an LLM with high-performing circuits from the elite set and instructs it to generate a new SPICE netlist, which is then evaluated by SPICE and selected using the same reward mechanism as conventional genetic operators.<n>Compared with the genetic framework without LLM guidance, LLM-SPICEMixer improves the median final training reward by 8.4% and the median validation-selected test reward by 8.8%.
  arXiv  Detail & Related papers  (2026-08-24T14:34:22Z)
• A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination [51.06539604709775]
  We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views.<n>A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory.
  arXiv  Detail & Related papers  (2026-08-05T14:01:10Z)
• LLM-as-a-Verifier: A General-Purpose Verification Framework [74.40111651545979]
  We introduce LLM-as-a-Verifier, a general-purpose verification framework.<n>It provides fine-grained feedback for agentic tasks without requiring additional training.<n>It achieves state-of-the-art performance on several benchmarks.
  arXiv  Detail & Related papers  (2026-07-06T17:59:35Z)
• ATLAS: Agentic Test-time Learning-to-Allocate Scaling [24.932203210615512]
  ATLAS is an agentic test-time scaling framework in which an LLM orchestrator owns the control loop end-to-end.<n>We evaluate ATLAS on four benchmarks covering scientific question answering, code generation, and multimodal reasoning.
  arXiv  Detail & Related papers  (2026-06-01T04:19:50Z)
• FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization [61.43300970020897]
  Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation.<n>Existing benchmarks are limited to small or simplified examples far below real-world scale and complexity.<n>We introduce FrontierOR, among the first benchmarks to evaluate LLM-based efficient algorithm design for realistic large-scale optimization problems.
  arXiv  Detail & Related papers  (2026-05-24T20:10:42Z)
• S-LCG: Structured Linear Congruential Generator-Based Deterministic Algorithm for Search and Optimization [3.033196534183858]
  This study presents a novel deterministic optimization algorithm based on a special variant of the Linear Congruential Generator (LCG)<n>It is motivated by the intrinsic structure of the generator, the reason behind naming it the Structured Linear Congruential Generator (S- LCG)
  arXiv  Detail & Related papers  (2026-05-06T17:57:41Z)
• Breaking Validity-Induced Boundaries to Expand Algorithm Search Space: A Two-Stage AST-Based Operator for LLM-Driven Automated Heuristic Evolution [0.0]
  We propose a two-stage, structure-based evolutionary operator for LLM-AHD.<n>In the first stage, our approach directly performs crossover and mutation on the Abstract Syntax Trees (ASTs) of code.<n>In the second stage, the LLM is employed to repair these invalids into executable, high-quality code.
  arXiv  Detail & Related papers  (2026-04-03T07:35:43Z)
• TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning [17.157244731153554]
  We formalize test suite generation as a MDP and demonstrate that its objective exhibits monotone submodularity.<n>We propose TestDecision, which transforms LLMs into neural greedy experts.<n>TestDecision significantly outperforms existing advanced methods.
  arXiv  Detail & Related papers  (2026-04-02T09:13:52Z)
• AIRA_2: Overcoming Bottlenecks in AI Research Agents [31.269750755536247]
  Existing research has identified three structural performance bottlenecks in AI research agents.<n>We introduce AIRA$$, which addresses these bottlenecks through three architectural choices.<n>On MLE-bench-30, AIRA$$ achieves a mean Percentile Rank of 71.8% at 24 hours - surpassing the previous best of 69.9%.
  arXiv  Detail & Related papers  (2026-03-27T15:02:43Z)
• Prism: Efficient Test-Time Scaling via Hierarchical Search and Self-Verification for Discrete Diffusion Language Models [96.0074341403456]
  Inference-time compute has re-emerged as a practical way to improve LLM reasoning.<n>Most test-time scaling (TTS) algorithms rely on autoregressive decoding.<n>We propose Prism, an efficient TTS framework for dLLMs.
  arXiv  Detail & Related papers  (2026-02-02T09:14:51Z)
• From Memorization to Creativity: LLM as a Designer of Novel Neural-Architectures [48.83701310501069]
  Large language models (LLMs) excel in program synthesis, yet their ability to autonomously navigate neural architecture design-balancing reliability, performance, and structural novelty--remains underexplored.<n>We address this by placing a code-oriented LLM within a closed-loop synthesis framework, analyzing its evolution over 22 supervised fine-tuning cycles.
  arXiv  Detail & Related papers  (2026-01-06T13:20:28Z)
• MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges? [66.87201770167012]
  MLRC-Bench is a benchmark designed to quantify how effectively language agents can tackle challenging Machine Learning (ML) Research Competitions.<n>Unlike prior work, MLRC-Bench measures the key steps of proposing and implementing novel research methods.<n>Even the best-performing tested agent closes only 9.3% of the gap between baseline and top human participant scores.
  arXiv  Detail & Related papers  (2025-04-13T19:35:43Z)
• LLM2: Let Large Language Models Harness System 2 Reasoning [65.89293674479907]
  Large language models (LLMs) have exhibited impressive capabilities across a myriad of tasks, yet they occasionally yield undesirable outputs.<n>We introduce LLM2, a novel framework that combines an LLM with a process-based verifier.<n>LLMs2 is responsible for generating plausible candidates, while the verifier provides timely process-based feedback to distinguish desirable and undesirable outputs.
  arXiv  Detail & Related papers  (2024-12-29T06:32:36Z)
• LLaMA-Berry: Pairwise Optimization for O1-like Olympiad-Level Mathematical Reasoning [56.273799410256075]
  The framework combines Monte Carlo Tree Search (MCTS) with iterative Self-Refine to optimize the reasoning path. The framework has been tested on general and advanced benchmarks, showing superior performance in terms of search efficiency and problem-solving capability.
  arXiv  Detail & Related papers  (2024-10-03T18:12:29Z)
• A Multi-operator Ensemble LSHADE with Restart and Local Search Mechanisms for Single-objective Optimization [0.0]
  mLSHADE-RL is an enhanced version of LSHADE-cnEpSin, one of the winners of the CEC 2017 competition in single-objective optimization. Three mutation strategies such as DE/current-to-pbest-weight/1 with archive, DE/current-to-pbest/1 without archive, and DE/current-to-ordpbest-weight/1 are integrated in the original LSHADE-cnEpSin. LSHADE-cnEpSin is tested on 30 dimensions in the CEC 2024 competition on single objective bound constrained optimization.
  arXiv  Detail & Related papers  (2024-09-24T11:49:08Z)

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.