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
141 results for “keyword:"software"” in ICLR 2027. 39 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]ASNER: Adaptive Semantic Neighborhoods and Evidence-Grounded Refinement for Software Architecture Recovery▼4.3k2.00
[PDF]HDPO: Aligning Large Language Models to Software Architecture via Hierarchical Preference Optimization▼1.2k1.67
[PDF]DySCoR: Stage-Constrained Dynamic Sparse Context Routing for Repository-Level Code Repair▼4.3k2.00
[PDF]Better Risk Hypotheses, Better Code Reviews? Diagnosing Risk Formulation and Prioritization in LLMs▼1351.33
[PDF]A Decade in a Day: Synthesizing Agent-Native Interfaces from Human-Oriented Software Evolution▼5.9k2.50
[PDF]SAR-Arena: Benchmarking Agent-Driven Research on AI Computing Systems and Architecture▼4.3k2.00
[PDF]SPINE: Structured Policy Refinement with Intent-to-Execution Lineage for LLM Software Agents▼4.3k2.00
[PDF]Reliable and Efficient Agent Loops for Reinforcement Learning on Software Engineering Tasks▲6.1k2.00
[PDF]Delete or Preserve? An Empirical Study of the Effects of Deletion and Preservation Instructions on AI-Generated Code▲11.00
[PDF]Evaluation Is an Intervention: How Evaluation Protocols Shape Measured LLM Program-Repair Performance▼1.2k1.67
[PDF]Beyond Rejection Sampling: Learning from Guided Rollouts to Improve LLMs for Software Engineering▼4.3k2.00
[PDF]LunarZero: A Single-Binary Coding Agent that Runs on Pooled Free-Tier Language Models with Quota-Aware Failover▼1.3k1.75
[PDF]ShapingBench: Can Coding Agents Reproduce Mature Software Behavior Beyond Explicit Requirements?▼4.5k2.67
[PDF]ASSERT: Synthesizing Replay-Verified Trajectories with Access Isolation for Software Engineering Agents▲5103.00
[PDF]Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents▼4.3k2.00
[PDF]WebProgramBench: Can Coding Agents Reconstruct Live Applications from Scratch via Black-Box Interaction?▲153.33
[PDF]ScienceCUA: Resource-to-Skill Construction and Execution-Guided Skill Evolution for Scientific Computer Use Agents▼4.5k2.67
[PDF]VeilPRBench: Can Code Review Agents Catch Vulnerabilities in Pull Requests That Resolve Real Issues?▼4.3k2.00
Withdrawn or desk rejected (39)
[PDF]When Unsupported Claims Become Working State: Measuring Ratification in Sequential AgentsDesk rejected
[PDF]TraceGate: Randomized Support Calibration for Local Retrieval Edits in Repeated AgentsDesk rejected
[PDF]BudgetWeaver: Learning the Downstream Value of Agent Reads and Memory Mutations under Shared BudgetsDesk rejected