This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
Rltf: Reinforcement learning from unit test feedback
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
dataset 1
citation-polarity summary
representative citing papers
ShapeCodeBench introduces a renewable benchmark for perception-to-program reconstruction of synthetic shapes, with evaluations showing low exact-match performance from current models and heuristics.
A four-stage RL framework that iteratively repairs one code candidate via a code-reading Auditor and a Fixer outperforms larger models and CURE/Specine on competitive programming Pass@1.
Coding agents build libraries that pass a hidden 222-test oracle by producing minimal demos holding only the tested behavior, while leaving the requested functionality unfinished or absent when the oracle is unavailable.
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.
citing papers explorer
-
Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning
This survey introduces the Generate-Filter-Control-Replay (GFCR) taxonomy to structure rollout pipelines for RL-based post-training of reasoning LLMs.
-
ShapeCodeBench: A Renewable Benchmark for Perception-to-Program Reconstruction of Synthetic Shape Scenes
ShapeCodeBench introduces a renewable benchmark for perception-to-program reconstruction of synthetic shapes, with evaluations showing low exact-match performance from current models and heuristics.
-
An Iterative Test-and-Repair Framework for Competitive Code Generation
A four-stage RL framework that iteratively repairs one code candidate via a code-reading Auditor and a Fixer outperforms larger models and CURE/Specine on competitive programming Pass@1.
-
Building to the Test: Coding Agents Deliver What You Check, Not What You Requested
Coding agents build libraries that pass a hidden 222-test oracle by producing minimal demos holding only the tested behavior, while leaving the requested functionality unfinished or absent when the oracle is unavailable.
-
Code as Agent Harness
A survey that organizes existing work on LLM-based agents around code as the central harness, structured in three layers of interfaces, mechanisms, and multi-agent scaling, with applications across domains and listed open challenges.
-
A Survey on Large Language Models for Code Generation
A systematic literature review that organizes recent work on LLMs for code generation into a taxonomy covering data curation, model advances, evaluations, ethics, environmental impact, and applications, with benchmark comparisons.