NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
172 results for “keyword:"code generation"” in ICLR 2027. 32 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Learning Across Roles: Role-Balanced Shared-Policy Optimization for Multi-Agent Code Generation▲3.8k2.50
[PDF]AutoFHE-Bench: Beyond Pass Rates in Agent-generated Fully Homomorphic Encryption Programs▼1351.33
[PDF]ShapingBench: Can Coding Agents Reproduce Mature Software Behavior Beyond Explicit Requirements?▼4.5k2.67
[PDF]CLOAKFEM: Agentic FEM Code Generation for Red-Teaming Computational Resource Exhaustion▲13k2.33
[PDF]MoldCoder: Automated Construction of Code Instruction Data Using Real Test Execution as Functional Supervision▲4012.67
[PDF]AlgoSAGE: Formal Problem Representation and Grounded Expertise for Algorithmic Code Generation▲4012.67
[PDF]XGenerator: Skill-Guided Synthesis of Verifiable Training Data for a Low-Resource Modeling Language▼4.3k2.00
[PDF]AuXSpec: Learning to Autoformalize Program Specifications via Executable Postconditions▲1.7k3.33
[PDF]ClarifyCodeBench: Evaluating LLMs on Clarifying Underspecified Requirements for Code Generation▼5.8k2.33
[PDF]Contra: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation▼5.8k2.33
[PDF]RELIVE-OR: Retrospective Learning through Integrated Validation of Experience for Operation Research Modelling▲6.1k2.00
[PDF]From Similar Code to Neural Correspondence: Causal Interventions Guided by Program Structure▼5.8k2.33
[PDF]PlayTrain: An Efficient Reinforcement Learning Framework for LLM-Generated Adaptable JavaScript Games▼4.5k2.67
[PDF]PairDistill: Amortizing Test-Time Pairwise LLM Oracles for Code Selection via Pairwise Judgment Distillation▼1.2k1.67
Withdrawn or desk rejected (32)
[PDF]Guided Reasoning Across ISA Dialects: Inference-Time Control for GPU Assembly TranslationWithdrawn1.67
[PDF]EffiPair: Improving the Efficiency of LLM-generated Code with Differential Execution FeedbackWithdrawn1.67