A code-graph and correction-based LLM search framework outperforms full-algorithm generation at equal token budgets on three combinatorial optimization problems.
hub Canonical reference
arXiv preprint arXiv:2504.05108 , year=
Canonical reference. 83% of citing Pith papers cite this work as background.
11
Pith papers citing it
Background
83% of classified citations
abstract
Discovering efficient algorithms for solving complex problems has been an outstanding challenge in mathematics and computer science, requiring substantial human expertise over the years. Recent advancements in evolutionary search with large language models (LLMs) have shown promise in accelerating the discovery of algorithms across various domains, particularly in mathematics and optimization. However, existing approaches treat the LLM as a static generator, missing the opportunity to update the model with the signal obtained from evolutionary exploration. In this work, we propose to augment LLM-based evolutionary search by continuously refining the search operator - the LLM - through reinforcement learning (RL) fine-tuning. Our method leverages evolutionary search as an exploration strategy to discover improved algorithms, while RL optimizes the LLM policy based on these discoveries. Our experiments on combinatorial optimization tasks demonstrate that integrating RL with evolutionary search accelerates the discovery of superior algorithms, showcasing the potential of RL-enhanced evolutionary strategies for algorithm design.
hub tools
citation-role summary
background 5
baseline 1
citation-polarity summary
representative citing papers
AHD Agent trains a 4B-parameter LLM via agentic RL to actively use tools for automatic heuristic design, matching or exceeding larger baselines across eight domains with fewer evaluations.
MLS-Bench is a benchmark with 140 tasks that evaluates AI agents on inventing generalizable and scalable ML methods, finding they lag human performance especially in insight-driven invention rather than tuning.
A knowledge-first approach to LLM-driven automatic heuristic design in combinatorial optimization yields better discovery efficiency, transfer, and generalization than code-centric baselines by formalizing a distortion-compression trade-off.
k-server-bench formulates potential-function discovery for the k-server conjecture as a code-based inequality-satisfaction task; current agents fully solve the resolved k=3 case and reduce violations on the open k=4 case.
TTT-Discover applies test-time RL to set new state-of-the-art results on math inequalities, GPU kernels, algorithm contests, and single-cell denoising using an open model and public code.
AlphaEvolve is an LLM-orchestrated evolutionary coding agent that discovered a 4x4 complex matrix multiplication algorithm using 48 scalar multiplications, the first improvement over Strassen's algorithm in 56 years, plus optimizations for Google data centers and hardware.
GrandCode is the first AI system to consistently beat all human participants and place first in live Codeforces competitive programming contests.
RL4RLA is a reinforcement learning framework that discovers interpretable symbolic randomized linear algebra algorithms by combining curriculum learning and graph-based search to overcome sparse rewards and large search spaces.
Case study applies verifier-guided LLM evolutionary agents to contraction-order optimization in tensor networks and concludes that human validation remains essential.
Lark is a biologically inspired neuroevolution framework for multi-stakeholder LLM agents that iteratively generates, refines, and selects strategies using plasticity, duplication/maturation, influence-weighted Borda scoring, and token penalties, achieving top-3 performance in 80% of 30-round trials
citing papers explorer
No citing papers match the current filters.