Augur is a synthetic decision laboratory that simulates how users will react to product and policy changes before they are released. It constructs a typed knowledge graph from change documents, populates a persona market, runs simulations, and produces an auditable decision memo recommending one of five actions. Using a dataset of 50 real episodes (Gold‑50), the authors evaluate the system’s five‑way release verdicts and find that evaluation design, rather than model capability, largely drives performance differences among frontier and open‑weight models.
By Rahul Khedar, Mayank Malhotra, Avinash Karn
JuryProbe is an empirical diagnostic tool designed to assess consensus risk in panels of reference‑free large language model judges used for factuality verification. It estimates risk by measuring false‑negative correlations and false‑consensus lift from a labeled calibration probe, and routes high‑risk majority decisions to judges with trusted references. The approach was validated on FEVER corruptions, showing that flagged decisions can be grounded without additional reference acquisition in most cases, while reducing false accepts by about 0.4% and avoiding 28% of reference acquisitions.
By Tianxin Zhou, Ruixi Lin
The paper compares a non‑generative verifier (Jev) with a frontier LLM (Astra) on 495 human‑labelled claims from LLM‑AggreFact. Both models achieve statistically indistinguishable accuracy, yet Jev is 187‑fold cheaper and admits more unsupported claims. A confidence‑gated cascade that escalates uncertain claims improves cost‑efficiency, though the benefit comes mainly from the escalation share rather than the probability estimates.
By Alden Do Rosario, Kirollos Atef
arXiv:2609.07944v1 Announce Type: new
Abstract: Existing causal-inference benchmarks for LLMs mostly score method descriptions or whether generated code runs, not whether the executed workflow recove...
By Yonghong Zhang, Ricardo Correia, Isabel M. Parra, Yong Xie
The paper treats human interventions during LLM agent failures as labels that pinpoint the internal computation that went wrong, rather than merely training data. In a controlled environment, the authors analyze one failure type—over‑asking a clarifying question when the request is already clear—using rule‑based overseer labels validated by blind human judgment. They find that the decision to ask versus act can be causally localized across several models, that over‑asking exhibits distinct mechanistic signatures, and that steering or weight consolidation can mitigate the issue, though outcomes vary by model family.
By Cesare Zavattari, Alessandro Tommasi, Giuseppe Prencipe
The paper introduces CERTID, a formal identification pipeline that uses the sound and complete causal identification algorithm ID to certify whether a causal effect is identifiable from a given graph and query. CERTID also verifies returned formulas against structural causal models with known interventional distributions, mitigating structural leakage and providing grading guarantees. The authors evaluate three frontier reasoning models on 1,200 certified instances, finding that accuracy is a poor proxy for soundness, with false-claim rates on non-identifiable queries varying by seventeen-fold across models.
By Arman Behnam, Binghui Wang
arXiv:2607. 18828v1 Announce Type: new Abstract: Readiness stress-testing of medical AI has focused on closed-ended and multimodal benchmarks.
By Koyar Afrasyab
The paper investigates whether fast, cost‑efficient decision models can classify the type of conflict among retrieved sources for a query, a task that improves response quality when the conflict type is known. Using the CONFLICTS benchmark, the authors evaluate 11 commercial decision models against Gemini LLMs, finding that most achieve 50–67% accuracy, often matching or surpassing Gemini 2.5 Flash while incurring 4–39× lower cost and 2.6–6.0× lower latency. A cascade approach that forwards uncertain cases to Gemini 3.8 Flash yields comparable performance at only 25–37% of its cost, and the resulting typed responses generally behave as expected when compared to LLM‑derived types.
By Parv Khatri, Harshul Jain, Mehak Kapoor, Tanya Sah
The paper presents a clinician‑led safety guardrail for mental‑health chatbots that replaces typical prompt‑engineering or Constitutional AI methods. Two clinicians design, finalize, and adjudicate a rule base of four safety checks, which is formally verified for internal consistency and applied to LLM outputs. The verification layer’s verdicts are recomputable from a named rule and sixteen facts, and it consistently avoids false crisis‑resource demands that a matched LLM judge frequently raises.
By Chenhan Lyu, Kit Wislocki, Sarah Elizabeth Stoeckl, Maitreyi Sinha, Amir Rahmani
The paper introduces a counterfactual evidence audit to assess how large language model agents respond to different sets of documents. By exposing agents to two mirrored sets of five documents and measuring changes in six downstream decisions, the authors predict how the agents will behave when presented with a full 45‑document context. Across multiple open‑weight model families and tasks, the five‑document audit accurately forecasts full‑context effects, reducing prediction error by 62% and correctly identifying the direction of most material effects.
By Rana Muhammad Usman
arXiv:2610.41025v1 Announce Type: new
Abstract: When a language-model agent fails a multi-step task, can another model find the decisive mistake and fix it with a single action? We introduce ReplayRC...
By Jeremy Canale, Fabien Soulis
arXiv:2606. 08275v1 Announce Type: cross Abstract: When an LLM agent fails -- issues a refund it should not have, calls the wrong tool, leaks data -- existing tooling answers what happened (observability) or whether it passed (evaluation), but not which step caused the failure.
By Jaineet Shah