Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
Planning in natural language improves LLM search for code generation.arXiv preprint arXiv:2409.03733
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 7roles
background 1polarities
background 1representative citing papers
AdverMCTS frames code generation as a minimax game where an attacker evolves tests to expose flaws in solver-generated code, yielding more robust outputs than static-test baselines.
OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compete with much larger ones.
Fine-tuning LLMs on a novel, syntax-friendly but feature-poor language teaches parsing without closing the gap between PyLang and Python pass rates.
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
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.
Meta's safety report states that Muse Spark meets acceptable risk thresholds for release after mitigations reduced elevated pre-mitigation risks in chemical and biological domains.
citing papers explorer
-
Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models
Preregistered placebo-controlled decomposition shows external executable counterexamples drive self-repair gains in small code models more than re-exposure or self-critique.
-
AdverMCTS: Combating Pseudo-Correctness in Code Generation via Adversarial Monte Carlo Tree Search
AdverMCTS frames code generation as a minimax game where an attacker evolves tests to expose flaws in solver-generated code, yielding more robust outputs than static-test baselines.
-
OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation
OPD-Evolver uses on-policy self-distillation in fast interaction and slow attribution loops to build agents with holistic memory competence, outperforming prior systems by up to 11.5% and allowing a 9B model to compete with much larger ones.
-
Syntax Without Semantics: Teaching Large Language Models to Code in an Unseen Language
Fine-tuning LLMs on a novel, syntax-friendly but feature-poor language teaches parsing without closing the gap between PyLang and Python pass rates.
-
Evaluation-driven Scaling for Scientific Discovery
SimpleTES scales test-time evaluation in LLMs to discover state-of-the-art solutions on 21 scientific problems across six domains, outperforming frontier models and optimization pipelines with examples like 2x faster LASSO and new Erdos constructions.
-
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.
-
Muse Spark Safety & Preparedness Report
Meta's safety report states that Muse Spark meets acceptable risk thresholds for release after mitigations reduced elevated pre-mitigation risks in chemical and biological domains.