Fetching from the wire…
01
02
03
04
05
06
07
08
Public story · 2026-08-03 · high
AuditCoder's own audit of 200 test cases found its failure locator catches the broken node only 26 times out of 60.
Why now: The paper is the coding-agent entry in the August 3 research roundup, benchmarked directly against AgentCoder rather than reported alone.
AuditCoder pairs generated code with a contract-annotated trace that ties every commitment, implementation, and piece of validation evidence to a stable identity, according to a paper posted to arXiv.
That's aimed at anyone who has to explain why a generated function does what it does, not just whether it passes. On the APPS benchmark, AuditCoder hit 82.5 to 83.0% pass@1; on ClassEval, 75.0 to 82.0%. Both numbers beat a CoT-plus-retry baseline, and both trail AgentCoder.
When a test fails, a locator tries to trace the failure back to one node in the task graph, or abstain instead of guessing wrong. Find the node, and bounded repair regenerates only that piece of the graph rather than the whole program.
The paper's own audit of 200 APPS records shows why that matters. Trace coverage held at 97.25%, so nearly every run produced a complete record. The locator, though, pinned the actual failing node in just 26 of the 60 failure cases it looked at.
What AuditCoder actually proves is that a near-complete audit trail and an accurate diagnosis are two different problems. Right now, it's only solved one of them. The paper is the coding-agent entry in the August 3 research roundup, benchmarked directly against AgentCoder rather than reported alone.
Each link below shares sources, entities, or timing with this story.
Shared entity: CoT / Same source domain / Earlier coverage
Both cover CoT; reported by the same outlet (arxiv.org); earlier CoT coverage from 2026-04-02.
Both cover CoT; reported by the same outlet (arxiv.org); earlier CoT coverage from 2026-03-07.
Both cover CoT; reported by the same outlet (arxiv.org); earlier CoT coverage from 2026-03-03.
Shared entity: Apps / Shared topic / Earlier coverage
Both cover Apps; overlapping topics (apps, evidence); earlier Apps coverage from 2026-03-03.
Shared entity: CoT / Same source domain / Earlier coverage
Both cover CoT; reported by the same outlet (arxiv.org); earlier CoT coverage from 2026-02-16.
Same source domain / Shared topic / Tension
Reported by the same outlet (arxiv.org); overlapping topics (apps, binding); pushes against this story (but).
Shared entity: CoT / Earlier coverage / Tension
Both cover CoT; earlier CoT coverage from 2026-06-08; pushes against this story (but).
Shared entity: Apps / Earlier coverage / Tension
Both cover Apps; earlier Apps coverage from 2026-04-16; pushes against this story (vs).