The paper introduces inexpensive, scalable methods for evaluating language model behavior across different vendors and releases. By running identical public stimuli on a cross‑vendor panel and analyzing transcripts via exact match, LLM‑coded codebooks, or instrumented environments, the authors can quantify model responses at a cost of a few dollars per model. Applying these tools to four years of releases reveals patterns of convergence, resistance, positional stability, and compliance that vary by generation, lab, and harness.
By Tapan Parikh
arXiv:2607. 20527v1 Announce Type: new Abstract: Agentic LLM systems such as OpenScholar and PaperQA2 read the scientific literature and return cited answers, and both they and their benchmarks already check whether those citations hold, with a fixed attribution model or human graders.
By Taewan Goo, Junsik Kim, Kyulhee Han, GwonYul Jo, Jong-Soo Kim, Tae-Hyung Kim
arXiv:2607. 18360v1 Announce Type: cross Abstract: Large language models (LLMs) now routinely draft literature reviews and assist with academic writing, which means a higher risk of fabricated references: GPTZero found 53 papers with hallucinated citations among NeurIPS 2025's accepted set.
By Patrik Reizinger, Wieland Brendel
arXiv:2607. 19257v1 Announce Type: cross Abstract: Practitioners make three prompt-design decisions with almost no controlled evidence behind them: how to format instructions and context (markdown, plain text, prose, or tabular), how many simultaneous instructions a system prompt can carry before compliance degrades, and how much context a model can hold before recall and honesty degrade.
By Netanel Eliav
OpenDiscoveryTrace is a public dataset of 558 complete AI scientific agent trajectories that records the reasoning process—thoughts, tool calls, observations, errors, revision triggers, and confidence—across 124 scientific tasks in drug discovery, materials science, genomics, and literature analysis. The dataset includes seven models (three frontier models and four open‑weight models) and 60 live‑retrieval variants, providing a balanced view of performance and error patterns. Pilot analysis shows that process traces reveal behavioral differences invisible to output‑only evaluation, such as differing error rates and types among frontier models.
By Aayam Bansal, Keertan Balaji
arXiv:2606. 10457v1 Announce Type: new Abstract: Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved through iterative error analysis.
By Junli Zha, Jinbo Wang, Chao Zhou, Xiang Song
arXiv:2606. 09500v1 Announce Type: new Abstract: Objective.
By Yoojin Nam, Jinhoon Jeong, Namkug Kim
arXiv:2608. 04278v1 Announce Type: cross Abstract: Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it.
By Hwai-Jung Hsu, Cheng-Jan Chi, Hanna Everett
TRACE is a system designed to bridge the grounding contract gap in LitTraceQA by combining target-aware retrieval, independent typed evidence localization, multimodal table extraction, and schema-driven table construction. It indexes 27,487 papers using multiple representations while preserving question targets, predicts observation units for tables, and assembles rows with evaluator-compatible key normalization. On the official test set, TRACE achieves a 0.760613 overall score, with high paper F1, evidence F1, and multiple-choice accuracy, though table-row and macro cell performance remain lower.
By Sachin Gupta, Divya Godara
arXiv:2607. 04579v1 Announce Type: cross Abstract: CI/CD workflows have become executable operational policy: they decide what gets built, tested, released, and deployed, and they mediate how maintainers interact with delivery infrastructure.
By Bonan Shen, Jiazhou Gao, Tao Ning, Wei-Jung Huang, Xin Liu
arXiv:2606. 09046v1 Announce Type: new Abstract: Useful audits reveal not only how often a model fails, but also where its failures concentrate.
By Vyzantinos Repantis, Ameya Gawde, Harshvardhan Singh
arXiv:2604. 16706v2 Announce Type: replace Abstract: Automated evaluation of tool-using large language model (LLM) agents is widely assumed to be reliable, yet this assumption is rarely validated against human annotation.
By Bhaskar Gurram