LLM agents have been increasingly adopted for security-focused code review, but existing benchmarks mostly derive the reviewed changes from their later fixes instead of the real-world bug-introducing commits. In this paper, we present SecPRBench, the first comprehensive benchmark for evaluating agentic security review...
Yi-Han Yang, Chenyuan Yang, Zi-Jie Zhao et al.
· 1 citation
· ⚡1
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
Jul 2026
Tencent WorkBuddy Bench is introduced, a multi-domain evaluation suite for coding agents, and its construction methodology, scoring protocol, and a cross-model leaderboard are documents, with a cross-model leaderboard across several model families.
Si-Qi Cai, Shao-Peng Chen, Xiang Fei et al.
· arXiv.org · 4 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓
Jul 2026
This position paper argues that to claim a "long-horizon failure", benchmarks must compare actual full-task success against a baseline prediction built from short, individual stages, and calls the log-ratio between this prediction and actual success the horizon residual.
Chao Peng, Zhiheng Lyu, Peijie Dong et al.
· arXiv.org · 0 citations
Save
{ copied = true; setTimeout(() => copied = false, 1500) })"
class="icon-btn" aria-label="Copy link">
{ copied = 'apa'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy APA
Copied ✓
{ copied = 'mla'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy MLA
Copied ✓
{ copied = 'bibtex'; setTimeout(() => { copied = null; open = false }, 1000) })"
class="flex w-full items-center justify-between rounded-lg px-3 py-2 text-left text-sm hover:bg-gray-100 dark:hover:bg-ink-800">
Copy BibTeX
Copied ✓