2 papers
cs.SE2026
Coding Agents as Test-Suite Auditors: Finding What Official Suites Miss While Approaching What They Catch
Shuyang Xie, Shuxiao Xie, Feng Zhu +2
Online-judge verdicts and the datasets and benchmarks built on them are treated as ground truth for evaluating and training large language models for code. Yet prior audits have so…
cs.CV2026
Position Rebinding Cache Reuse: Replay-Free Visual Revisiting for Interleaved Multimodal Reasoning
Mengzhao Wang, Yanli Ji, Wangmeng Zuo +2
Interleaved multimodal reasoning improves visual grounding by revisiting visual evidence during multi-step generation, yet existing methods typically rely on token replay, repeated…