Fine-tuned 7B LLMs generating unified diffs for neural architecture refinement achieve 66-75% valid rates and 64-66% mean first-epoch accuracy, outperforming full-generation baselines by large margins while cutting output length by 75-85%.
arXiv preprint arXiv:2402.02172 , year=
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
representative citing papers
LLM agents inject CWEs into student-authored code to generate personalized security examples; in a 71-student deployment, participants rated them more relevant than textbook cases but quantitative differences remained limited.
AgensFlow learns coordination policies from task trajectories and outperforms fixed pipelines on distributed-systems incident and security-advisory tasks.
XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
Coding agents have reached a capability level where human code review is no longer necessary because agents can serve every review goal more efficiently and the hybrid human-reviewer model does not scale.
citing papers explorer
-
Delta-Based Neural Architecture Search: LLM Fine-Tuning via Code Diffs
Fine-tuned 7B LLMs generating unified diffs for neural architecture refinement achieve 66-75% valid rates and 64-66% mean first-epoch accuracy, outperforming full-generation baselines by large margins while cutting output length by 75-85%.
-
Towards Personalizing Secure Programming Education with LLM-Injected Vulnerabilities
LLM agents inject CWEs into student-authored code to generate personalized security examples; in a 71-student deployment, participants rated them more relevant than textbook cases but quantitative differences remained limited.
-
AgensFlow: A Coordination-Policy Substrate for Multi-Agent Systems
AgensFlow learns coordination policies from task trajectories and outperforms fixed pipelines on distributed-systems incident and security-advisory tasks.
-
XSearch: Explainable Code Search via Concept-to-Code Alignment
XSearch achieves 15x gains on out-of-distribution code search benchmarks by replacing global embedding similarity with explicit concept-to-statement alignment.
-
Memory in the Age of AI Agents
The paper maps agent memory research via three forms (token-level, parametric, latent), three functions (factual, experiential, working), and dynamics of formation/evolution/retrieval, plus benchmarks and future directions.
-
The End of Code Review: Coding Agents Supersede Human Inspection
Coding agents have reached a capability level where human code review is no longer necessary because agents can serve every review goal more efficiently and the hybrid human-reviewer model does not scale.