A preregistered benchmark isolating the causal effect of prompt formulation on agent work across six open-weight reasoning models and a frontier closed model is presented, consistent with recent evidence that consequential computation can occur without an interpretable trace.
This work uses LAST-CQ -- a five-agent, training-free, execution-grounded Text-to-Cypher framework -- as an instrumented testbed, running three counterfactuals over 2,471 live-database queries and six backbones spanning three vendor scale tiers.
I. Prokopiou, Athanasios Aidinis, Panagiotis-Christos Kyrmpatsos et al.· 0 citations
A fast-growing ecosystem of plugins, skills, and prompt packs promises to make AI coding agents cheaper. The most popular single artifact—a "talk-like-a-caveman" skill for a widely used coding agent—has ~92,000 GitHub stars (as of 2026-07) and advertises a 65% token reduction. We show that such claims, though not fabri...
Erdni Zergetaev· Proceedings of the 1st Inter...· 0 citations
The evidence supports mimeo as a compact, inspectable reference on a person, not as a demonstrated transfer of their judgment; the evidence supports mimeo as a compact, inspectable reference on a person.
AI agents are increasingly being programmed to automate knowledge work over large collections of unstructured data. Such automation requires repeatability: when the underlying evidence is unchanged, the agent's categories, priorities, and counts should not shift materially between runs, even if each individual answer a...
This work introduces EAVer, an End-to-end Agentic Verifier that learns to control the complete response-level verification workflow as a unified policy, and construct 794 bidirectional same-trajectory preference pairs that keep claim grouping, search, and evidence fixed, enabling decision-focused Direct Preference Opti...
Ke-Ning Zheng, Ao-Ying Zheng, Zhi-Gang Chang et al.· 0 citations
RefactorPlatform, an open-source evaluation harness that holds the environment fixed and varies each design axis explicitly: model backbone, execution regime, and prompt specificity, is presented.
Aziz Ben Amor, Drish Mali, M. Acharya et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
