EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
Group-Evolving Agents: Open-Ended Self-Improvement via Experience Sharing, February 2026.https://arxiv.org/abs/2602.04837
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 7verdicts
UNVERDICTED 7roles
background 1polarities
background 1representative citing papers
Empirical study of EvoMap shows 98% of assets never reused, scores driven by self-reported metadata, and 84% of assets using vacuous validation tests.
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.
Shepherd provides a reversible execution trace substrate for LLM agents that enables meta-agents to inspect and transform runs, yielding reported gains on coding and terminal benchmarks via supervision, counterfactual repair, and RL credit assignment.
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
ContractSkill converts draft web agent skills into explicit executable contracts that enable deterministic verification, fault localization, and minimal local repair, improving stability on benchmarks like VisualWebArena.
RQGM enables co-evolution of agents and evaluators across epochs with non-stationary utilities, reporting gains in coding pass rates, paper acceptance, and proof grading over prior self-improving agents.
citing papers explorer
-
EvoRepair: Enhancing Vulnerability Repair Agents Through Experience-Based Self-Evolution
EvoRepair is the first experience-based self-evolving agent framework for automated vulnerability repair, reporting 90.46% overall success on PATCHEVAL and SEC-bench benchmarks.
-
Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network
Empirical study of EvoMap shows 98% of assets never reused, scores driven by self-reported metadata, and 84% of assets using vacuous validation tests.
-
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.
-
Shepherd: Enabling Programmable Meta-Agents via Reversible Agentic Execution Traces
Shepherd provides a reversible execution trace substrate for LLM agents that enables meta-agents to inspect and transform runs, yielding reported gains on coding and terminal benchmarks via supervision, counterfactual repair, and RL credit assignment.
-
AgentGA: Evolving Code Solutions in Agent-Seed Space
AgentGA optimizes agent seeds with genetic algorithms and parent-archive inheritance to improve autonomous code generation, beating a baseline on 15 of 16 Kaggle competitions.
-
ContractSkill: Repairable Contract-Based Skills for Multimodal Web Agents
ContractSkill converts draft web agent skills into explicit executable contracts that enable deterministic verification, fault localization, and minimal local repair, improving stability on benchmarks like VisualWebArena.
-
The Red Queen G\"odel Machine: Co-Evolving Agents and Their Evaluators
RQGM enables co-evolution of agents and evaluators across epochs with non-stationary utilities, reporting gains in coding pass rates, paper acceptance, and proof grading over prior self-improving agents.