Latest papers

CardsList

75 papers40 papers in the last four weeks, up 567% on the four weeks before. 0.3% of all new papers.

  1. MirrorCode: AI can rebuild entire programs from behavior alone

    Jun 29, 2026Tom Adamczewski, David Owen, David Rein +4Software Engineering AgentsAI Agent Benchmarks

  2. Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering

    Jun 16, 2026Maria I. Gorinova, Macey Baker, Amy Heineike +3AI Coding AgentsBenchmark Design

  3. Dialogue SWE-Bench: A Benchmark for Dialogue-Driven Coding Agents

    Jun 12, 2026Brendan King, Jeffrey FlaniganCoding AgentsLLM Agent Evaluation

  4. Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement

    Jun 4, 2026Xin Wang, Liangtai Sun, Yaoming Zhu +8Code GenerationLanguage Model Generation Evaluation

  5. TensorBench: Benchmarking Coding Agents on a Compiler-Based Tensor Framework

    Jun 4, 2026Bobby Yan, Fredrik KjolstadAI Coding AgentsBenchmark Design

  6. RealClawBench: Live OpenClaw Benchmarks from Real Developer-Agent Sessions

    Jun 2, 2026Zongwei Lv, Zhewen Tan, Yaoming Li +7Agent BenchmarksAI Coding Agents

  7. PithTrain: A Compact and Agent-Native MoE Training System

    May 29, 2026Ruihang Lai, Hao Kang, Haozhan Tang +6Mixture-of-Experts Language ModelsCoding Agent Benchmarks

  8. 1GC-7RC: One Graphic Card -- Seven Research Challenges! How Good Are AI Agents at Doing Your Job?

    May 16, 2026Robin-Nico Kampa, Fabian Deuser, Anna Bößendörfer +2AI Coding AgentsAI Agent Evaluation

  9. ProgramBench: Can Language Models Rebuild Programs From Scratch?

    May 5, 2026John Yang, Kilian Lieret, Jeffrey Ma +9Software Engineering AgentsSoftware Engineering Benchmarks

  10. SlopCodeBench: Benchmarking How Coding Agents Degrade Over Long-Horizon Iterative Tasks

    Mar 25, 2026Gabriel Orlanski, Devjeet Roy, Alexander Yun +7AI Coding AgentsCoding Agent Benchmarks

  11. FormulaCode: Evaluating Agentic Optimization on Large Codebases

    Mar 16, 2026Atharva Sehgal, James Hou, Akanksha Sarkar +4Scientific ComputingCoding Agent Benchmarks