Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
Self-Evolving Recommenda- tion System: End-To-End Autonomous Model Optimization With LLM Agents, February 2026
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
years
2026 7representative citing papers
SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to memory accumulation.
NeuroClaw is a domain-specialized multi-agent framework with NeuroBench benchmark that improves executability and reproducibility for multimodal neuroimaging research.
A verification-aware agent harness that proposes and semantically checks recommender architecture changes reported the best effective pass rates in Tencent's tests and positive GMV gains (+1.25% to +2.02%) in a production A/B test.
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
VirtualMLE deploys an LLM agent with execution-reflection-memory to tune sequential recommenders, reaching competitive quality on Amazon benchmarks with fewer trials and transferring heuristics across datasets.
AgenticRecTune deploys five LLM agents (Actor, Critic, Insight, Skill, Online) and a self-evolving Skillhub to handle end-to-end configuration optimization for multi-stage recommendation systems.
citing papers explorer
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
SAGER: Self-Evolving User Policy Skills for Recommendation Agent
SAGER equips LLM recommendation agents with per-user evolving policy skills via two-representation architecture, contrastive CoT diagnosis, and skill-augmented listwise reasoning, yielding SOTA gains orthogonal to memory accumulation.
-
NeuroClaw Technical Report
NeuroClaw is a domain-specialized multi-agent framework with NeuroBench benchmark that improves executability and reproducibility for multimodal neuroimaging research.
-
NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems
A verification-aware agent harness that proposes and semantically checks recommender architecture changes reported the best effective pass rates in Tencent's tests and positive GMV gains (+1.25% to +2.02%) in a production A/B test.
-
EvoRec: Self Evolving Agentic Recommender Systems
EvoRec deploys four collaborating LLM agents that co-evolve recommendation models and their optimization methods, reporting up to 5.54% offline gains and 1.85% revenue lift in an online A/B test.
-
VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders
VirtualMLE deploys an LLM agent with execution-reflection-memory to tune sequential recommenders, reaching competitive quality on Amazon benchmarks with fewer trials and transferring heuristics across datasets.
-
AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization
AgenticRecTune deploys five LLM agents (Actor, Critic, Insight, Skill, Online) and a self-evolving Skillhub to handle end-to-end configuration optimization for multi-stage recommendation systems.