CORTEXA
← Browse
arxivcs.SEcs.LG2026-07-01

The Moving Target: A Longitudinal Audit of Trustworthiness Drift Across Twelve Checkpoints of Open-Source Chat LLMs

Zhichao Fan, Yanhang Li, Zexin Zhuang, Xian Sun, Yingshuo Wang

Model cards quote trust-benchmark scores without recording when they were measured, and the same number is routinely carried across successive checkpoints of one release line as if the model behind it had not shifted. We test whether it has shifted by auditing four open-source release lines, Yi, Qwen, Mistral, and Gemma, at three successive generations each, on a fixed basket of trust benchmarks under multiple prompt templates. Mean absolute adjacent-generation drift lands well above an independence-based no-drift reference null, and the gap persists when we drop a benchmark, drop a release line, or switch to strict scoring. We therefore conclude that a trust score attached to a release line should not be carried forward to the next checkpoint without remeasurement; it should instead be reported as a checkpoint-bound, dated artefact, which we package as a longitudinal model card. Closed APIs, larger models, canonical benchmark protocols, and fixed month-cadence rules lie outside the audited scope and require their own evaluation.

View free PDFSource page

Related papers

arxivcs.SEcs.LG2026-07-08

DeepSWE: Measuring Frontier Coding Agents on Original, Long-Horizon Engineering Tasks

Wenqi Huang, Charley Lee, Leonard Tng, Serena Ge

DeepSWE is a benchmark of 113 original, long-horizon software engineering tasks for evaluating coding agents. Most public agentic coding benchmarks follow SWE-bench in mining merged fixes from public GitHub repositories, which creates two problems: the fixes and their discussion…

View free PDFSource page
arxivcs.LGcs.AIcs.CYcs.SE2026-07-14

Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs

Junyu Ren

Tool access alone does not make LLM empirical reasoning governable: accepted outputs need not descend from attested evidence, and accepted deductions need not hold up under formal scrutiny. We present EG-VAR (Evidence-Grounded Verified Agentic Reasoning), a Lean 4-based tool-call…

View free PDFSource page
arxivcs.CLcs.LGcs.SE2026-07-18

OpenLanguageModel: Readable and Composable Small-Language-Model Pretraining for Education and Research

Tavish Mankash, Vardhaman Kalloli, Keshava Prasad, Deepan Muthirayan

OpenLanguageModel (OLM) is an open-source PyTorch library for building and pretraining small language models while keeping their machinery visible. In OLM, model code reads like the architecture: components are ordinary modules, while Block, Residual, Repeat, and Parallel describ…

View free PDFSource page
arxivcs.LGcs.AIcs.SE2026-07-08

Gimitest: A Comprehensive Tool for Testing Reinforcement Learning Policies

Dennis Gross, Quentin Mazouni, Helge Spieker, Arnaud Gotlieb

Reinforcement learning (RL) policies can be unsafe and vulnerable to attacks. Ensuring their reliability is often a pain point as existing automated testing methods target only selected environments, testing scenarios, and RL algorithms. To address this, we propose a comprehensiv…

View free PDFSource page
arxivcs.SEcs.AIcs.LG2026-07-04

Don't Blame the Large Language Model: How Agent Harness Evolution Shapes Coding Agent Quality

Oussama Ben Sghaier, Hao Li, Bram Adams, Ahmed E. Hassan

Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agent harness: a middleware layer in between a developer and a large language model that orchestrates system prompts, tool execution, context management, and ite…

View free PDFSource page