arXiv:2608. 03744v1 Announce Type: new Abstract: Clinical decision support is moving toward committees of language-model agents deliberating on a shared workspace.
arXiv:2608.31016v1 Announce Type: cross Abstract: Ambient AI scribes draft clinical notes, and published audits find their dominant error is omission: information the encounter established that the n...
arXiv:2609.03221v3 Announce Type: replace-cross Abstract: Counterfactual fairness audits of clinical language-model agents report a flip rate: how often an action changes when only the patient's demo...
The paper introduces the twin‑prefix framework to evaluate how the size of the verification unit—i.e., how many actions a pre‑execution LLM monitor reviews in one call—affects its performance. By pairing each gold plan with a twin that differs by a single write and injecting a controlled error, the authors isolate the impact of review length on catch rates and false rejections. Their findings show that longer review windows increase rejection rates but do not improve discrimination, with the highest informedness occurring at one or two actions across all judges and domains.
SkillGate is a method that trains agents to select the correct skill from a large slate during an episode by separating credit signals for skill selection and execution. It addresses the problem of selector credit starvation, where traditional outcome-rewarded RL fails to give sufficient credit to the skill-naming tokens, especially in long-horizon tasks. Experiments on five benchmarks show that SkillGate improves a 9B policy’s success rate from 40.8% to 53.2%, reduces exposure to misleading candidates, and requires fewer skill reads.
The paper investigates how language‑model judges can make version‑dependent errors when evaluating upgraded agents. Using 35 public coding‑agent submissions, two customer‑service agents, and over a thousand expert‑labeled trajectories, the authors show that fixed judges often reject task‑conditioned error invariance and can incorrectly approve failed patches, especially as agent capability increases. Paired audits of current outputs reduce interval width only marginally, and the study concludes that independent human patch review is still necessary.
The paper introduces a new evaluation method called "same-input rerun" to assess the consistency of clinical language‑model agents across repeated runs. By replaying 1,000 MedAgentBench tasks with identical inputs, the authors find that action‑level outputs—such as test orders, medication requests, and referrals—vary significantly, even when benchmark scores remain unchanged. The study demonstrates that current benchmarks, which typically evaluate only a single run per task, can miss substantial behavioral divergence.
arXiv:2609.00654v1 Announce Type: new Abstract: We describe the SciTrue team's participation in both subtasks of the NTCIR-19 SciClaimEval task~\cite{sciclaimeval}, which asks systems to verify scien...
The paper reports that counterfactual fairness audits of clinical language‑model agents are unreliable without accounting for a per‑action instability floor. By repeatedly running identical vignettes, the authors found that actions changed 8.7% of the time, with instability varying eightfold across actions. A second model confirmed a pooled floor of 6.7%, showing that any reported fairness estimate lacking this floor cannot be interpreted as evidence of disparity.
arXiv:2608. 03190v1 Announce Type: new Abstract: Neuro-oncology decisions require coordinated interpretation of serial MRI, pathology, molecular markers, treatment history, performance status, and evolving guidelines.
arXiv:2606. 10315v1 Announce Type: cross Abstract: LLM-as-judge is the default instrument for evaluating conversational agents, yet its reliability is almost always reported as agreement with human ratings, not recall of real defects.
The paper investigates when a language‑model judge can truly ground its verdicts in code correctness. It shows that current multi‑agent verification methods rely on evidence that is both independent of the answer and distinct between candidates—conditions that fail in code judging. By analyzing two label‑free measurements from the judge’s logs, the authors demonstrate that gating on one measurement allows the system to decline uncertain comparisons, improving accuracy from 20.7% to 36.9% while still answering half of all cases.
The study examines a two‑agent résumé screening process where both employer‑side and candidate‑side agents exchange evidence before deciding who advances, contrasting it with the traditional one‑call automated screening. Using GPT‑5.5 and Claude Opus 4.7 on 600 constructed résumé‑job pairs, the two‑agent method increased the proportion of applications advanced (up to 39.3% for GPT‑5.5) and raised pass rates for borderline cases from 4.5% to 26.2% (GPT‑5.5) and 6.5% to 16.1% (Opus 4.7). The results show that the screening procedure itself, rather than just the underlying model, determines which candidates reach human review and how consistently that access recurs.