The paper evaluates hard‑gate candidacy for validators in a deployed generative‑agent system by measuring how well each validator’s firing separates successful from failed builds. Across 13 validators and thousands of builds, only a few checks show statistically significant separation, while many fail to distinguish or never fire. The study highlights that skipped checks are recorded as passes, limiting detectable failure rates and underscoring the need for clearer evaluation records.
By Xin Xu
arXiv:2606. 10241v1 Announce Type: new Abstract: Autonomous improvement loops are hard to trust because the improvement process is usually external scaffolding bolted onto the agent: failures go unlogged, diagnoses cannot be replayed, and promote-or-discard decisions land in a side database rather than the agent's own history.
By Yohei Nakajima
The paper introduces rebuild‑dossier, an open‑source tool that locks an application’s real interface before code is written and enforces one‑test‑at‑a‑time building through automated checks. In experiments, a compliant agent failed a held‑back test while a rule‑breaking agent passed, showing that a passing test suite can be gamed. The study also demonstrates that the automated check mechanism, rather than interface‑locking alone, is crucial for reliable rebuilds, and that multi‑level verification catches errors that single‑level checks miss.
By Parker Fawcett
The paper introduces ClaimReceipt, a specification and verifier that checks whether a claim in an agent evaluation can be recomputed from retained evidence (sufficiency) and whether the evidence covers the entire experiment set (coverage). Using the CR‑2 verifier on 1,392 historical records, the authors demonstrate accurate reproduction of audit verdicts, non‑redundant field groups, and zero false positives on semantic faults. In a prospective CR‑3 run, the system correctly flags missing receipts and preserves coverage when private evidence is withheld, while adding minimal overhead to inference time and transaction size.
By Peiying Zhu, Sidi Chang
arXiv:2610.16067v1 Announce Type: cross
Abstract: Agent evaluation harnesses are software systems that run test suites, generate inputs, and decide outcomes with test oracles. This paper audits such...
By Junjie Chen
The paper demonstrates that a verifier used in closed‑loop agent debugging can inadvertently reveal the answer it is meant to test, rendering solver comparisons meaningless. In a study of 12 development cases, both exact minimum hitting set and a greedy method returned identical supports, and an audit showed that exact‑anchor predicates always produced the planted fault pair. The authors propose a support‑gated verification contract that requires a clean reference map and runtime evidence before an independently calibrated signal can confirm a detection, and validate this approach on 1,440 held‑out cases with a low false‑admission rate.
By Peiying Zhu, Sidi Chang
arXiv:2607. 24604v1 Announce Type: cross Abstract: Generate--test--revise loops are common in coding agents, but repetition alone provides no reliability guarantee.
By Xueping Gao, Jianwei Yang, Qiang Yang
The paper presents a small coverage‑closure agent that verifies data integrity for LLM‑generated functional tests in hardware design. It reads coverage from simulation reports (cocotb‑coverage YAML) and uses separate scoreboards to check data, rather than relying on the model’s account. Applied to three different RTL designs—a FIFO, a UART transmitter, and an AHB2APB bridge—the agent increased coverage from 91.7%, 88.9%, and 67.4% to 100% within eight iterations, and also uncovered a clock‑domain‑crossing bug in a manual testbench.
By Venkata Krishna Kumar Vedantam
arXiv:2607. 11098v1 Announce Type: cross Abstract: Tool-using LLM agents are mostly evaluated assuming all tools work.
By Aritra Mazumder, Nusrat jahan Lia
arXiv:2605. 17450v2 Announce Type: replace-cross Abstract: As software systems grow increasingly complex, automated vulnerability repair (AVR) remains difficult because the materials available to a repair system are usually failure artifacts rather than repair guidance.
By Simiao Liu, Fang Liu, Peiding Wang, Taichuan Li, Yinghao Zhu, Xiaoli Lian, Li Zhang
The paper introduces a claim‑safe protocol for evaluating closed‑loop AI systems, consisting of three actions: Refuse, Decompose, and Refresh. It demonstrates the protocol in a simulator with 24 policy components and 1,440 held‑out cases, showing that abstention and stable false admission rates are low while providing detailed statistical diagnostics. The approach emphasizes that evaluation results should be tied to observable support and statistical calibration rather than a single PASS/FAIL label.
By Peiying Zhu, Sidi Chang
arXiv:2608. 02464v1 Announce Type: cross Abstract: LLM agents fail mid-episode -- they loop, cascade tool errors, drift off goal, fabricate results, or silently absorb corrupted content -- and the standard remedy, judging every step with a second LLM, costs more than the agent itself.
By Sunny Dubey