arXiv Machine Learning June 15, 2026 By Carlo Di Cicco

Code Correctness Signals in LLM Hidden States: Pre-Generation Probing and Repair Geometry

Read the original on arXiv Machine Learning →

arXiv:2606. 14530v1 Announce Type: new Abstract: Large language models encode rich information in their hidden states.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.

llms

arXiv Machine Learning

Jul 17

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation

arXiv:2606. 14530v3 Announce Type: replace Abstract: Large language models encode rich information in their hidden states.

By Carlo Di Cicco

llms

arXiv AI

Aug 3

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

arXiv:2607. 28871v1 Announce Type: cross Abstract: When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect.

By Xiaonan Xu, Wenjing Wu

llms agents

arXiv AI

1d ago

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

arXiv:2608. 16003v1 Announce Type: new Abstract: Automated checking pipelines increasingly place one language model as the checker and another (or the same one) as the fixer.

By Parsa Mazaheri, Kasra Mazaheri

llms robotics

arXiv Machine Learning

Jun 30

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

arXiv:2606. 30449v1 Announce Type: new Abstract: Probes on model internals could help monitor agentic systems if they identify harmful text or tool actions before those actions are generated.

By Max Fomin, Elad David, Amit LeVi

llms agents fine-tuning

arXiv AI

Jul 15

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

arXiv:2607. 12962v1 Announce Type: cross Abstract: Frozen small code LLMs are deployed locally, yet the information guiding a retry after a failed attempt is still measured without placebo controls in the self-repair literature.

By Mehmet Iscan

llms reinforcement-learning

arXiv Machine Learning

Jun 9

Decoy-Calibrated Failure Audits for Language Models

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

llms benchmarks

Related stories

Code Correctness Is Linearly Decodable from LLM Hidden States Before Generation

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

Prior Audit-Repair Context Shifts LLM Verifier Thresholds Toward Leniency

Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models

Decoy-Calibrated Failure Audits for Language Models