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
29 results for “keyword:"program repair"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Evolving with Feasibility: Turning Failures into Feedback for LLM-Driven Algorithm Evolution▲502.75
[PDF]DySCoR: Stage-Constrained Dynamic Sparse Context Routing for Repository-Level Code Repair▼4.3k2.00
[PDF]Fails Before Repair Is Not Enough: Auditing the Validity of Executable Repair Benchmarks.▼1351.33
[PDF]Evaluation Is an Intervention: How Evaluation Protocols Shape Measured LLM Program-Repair Performance▼1.2k1.67
[PDF]Not Every Failure Needs a Patch: PAUSE for Selective Program Repair under Uncertain Execution Feedback▼4.3k2.00
[PDF]If It Ain't Broke, Don't Fix It: Failures of Epistemic Control in Language-Model Agents▼4.3k2.00
[PDF]From Failures to Harness: Admission-Gated Runtime Patch Selection for Hard Harness Defects in LLM Agents▼1.2k1.67
[PDF]Rethinking Code Localization through Repair-Context Completeness: From Structural and Code Coverage Analysis to Context Augmentation▼1351.33
[PDF]MARS: Multi-Evidence Adaptive Search with State-Preserving Control for Repository-Level Program Repair▼4.3k2.00
[PDF]RepairChemist: Cross-Language Repair Skill Distillation for Low-Resource Program Repair▲5103.00
Withdrawn or desk rejected (5)
[PDF]Beyond Executability: Schema-Adaptive Alignment for Faithful Natural-Language-to-Symbolic ReasoningWithdrawn1.33
[PDF]BEHAVIORAL TEST DIVERSITY: QUANTIFYING TEST SUITE DIVERSITY THROUGH AGENTIC CODE REPAIRDesk rejected2.00