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
31 results for “keyword:"code agents"” in ICLR 2027. 5 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Inherited, Added, Or Ended Unresolved: Attribution Accounting For Warm-Started Coding Agents▲11.00
[PDF]Databox: Elevating SQL Debugging Agents with Instance-specific and Cost-Efficient Sandboxes▼5.8k2.33
[PDF]AFSIM-Agent: Hierarchical Self-Reflective Coding Agent for Cross-Language Adaptation to Unseen Scripting Languages▼1.2k1.67
[PDF]Fix-Test Collapse: Diagnosing and Resolving Self-Confirming Verification in Code Agents▼1.1k3.25
[PDF]PREDICTIVE, NOT REACTIVE: TASK FILTERING FOR COMPUTE-EFFICIENT GRPO TRAINING OF CODE AGENTS▼4.3k2.00
[PDF]ANTE: Anticipate, Then Execute - Learning Internal World Models for Code Agents from Verified Beliefs▼5.8k2.33
[PDF]Patches Hide Tests to Write: Deriving Trainable Test-Generation Tasks from Existing SWE Environments▼1.2k3.00
[PDF]KernelAudit: Can LLM-Generated GPU Kernels Be Both Reliable and Competitive on Real-World Workloads?▼4.5k2.67
[PDF]MemDev-Bench: Does Memory Help Code Agents? Benchmarking Memory Systems over Real Repository Histories▲4052.67
[PDF]DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch▼4.3k2.00
[PDF]TRACE-SWE: Trajectory Refinement with Action-oriented Execution Evidence for Code Agents▼4.3k2.00
[PDF]StatePortal: Agentic Checkpoint Synthesis for Testing Deep States in Interactive Software▼5.8k2.33