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
21 results for “keyword:"swe bench"” in ICLR 2027. 2 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[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]AsynCodeBench: Benchmarking Collaboration of Asynchronous Multi-Agent Systems in Software Engineering▼3.7k2.25
[PDF]LunarZero: A Single-Binary Coding Agent that Runs on Pooled Free-Tier Language Models with Quota-Aware Failover▼1.3k1.75
[PDF]Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents▼4.3k2.00
[PDF]Rethinking Code Localization through Repair-Context Completeness: From Structural and Code Coverage Analysis to Context Augmentation▼1351.33
[PDF]TraceGen: Synthesizing Difficulty-Controllable Bugs for Training and Evaluating Code Repair Agents▼1351.33
[PDF]Whose Outcome Is the Team's Score? Auditing Aggregation and Scored-Object Binding in Multi-Agent Evaluation▼12k1.67
[PDF]MARS: Multi-Evidence Adaptive Search with State-Preserving Control for Repository-Level Program Repair▼4.3k2.00