arXiv AI August 7, 2026 By Itamar Pres, Belinda Z. Li, Laura Ruis, Zifan Carl Guo, Keya Hu, Mehul Damani, Isha Puri, Ekdeep Singh Lubana, Jacob Andreas

Position: It's Time to Optimize LLMs for Self-Consistency

Read the original on arXiv AI →

arXiv:2608. 05188v1 Announce Type: cross Abstract: Despite ever-increasing sophistication in language model (LM) pre- and post-training pipelines, many important failures persist: models overcondition on user framing ("sycophancy"), exhibit incomplete logical generalization, and produce confident but incorrect responses.

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

arXiv AI

Jun 8

How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures

arXiv:2606. 06635v1 Announce Type: cross Abstract: Failures in language model reasoning emerge through distinct processes that leave identifiable signatures in the reasoning trace.

By Tanvi Thoria, Kiana Jafari, Marc R. Schlichting, Mykel J. Kochenderfer

llms

arXiv AI

Jul 1

The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes

arXiv:2606. 30653v1 Announce Type: cross Abstract: Large language models are increasingly deployed in agentic pipelines that depend on the model evaluating its own outputs without external verification.

By Marina Mancoridis, Zo\"e Hitzig

llms agents

arXiv AI

Jun 18

Self-CTRL: Self-Consistency Training with Reinforcement Learning

arXiv:2606. 18327v1 Announce Type: cross Abstract: Language models (LMs) that faithfully describe their own behavior can more easily be audited, understood, and trusted by users.

By Itamar Pres, Laura Ruis, Melat Ghebreselassie, Belinda Z. Li, Jacob Andreas

llms reinforcement-learning safety

arXiv Machine Learning

Aug 4

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

arXiv:2507. 02778v3 Announce Type: replace-cross Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths.

By Ken Tsui

llms fine-tuning safety

arXiv AI

Jun 3

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

arXiv:2602. 10352v2 Announce Type: replace-cross Abstract: Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitivity.

By Keenan Pepper, Alex McKenzie, Florin Pop, Stijn Servaes, Martin Leitgab, Mike Vaiana, Judd Rosenblatt, Michael S. A. Graziano, Diogo de Lucena

llms safety

arXiv AI

Jun 30

Translating Natural Language to Strategic Temporal Specifications via LLMs

arXiv:2606. 30441v1 Announce Type: cross Abstract: A rigorous formalization of system requirements is a fundamental prerequisite for the verification of Multi-Agent Systems (MAS).

By Marco Aruta, Francesco Improta, Vadim Malvone, Aniello Murano, Vladana Perlic

llms agents fine-tuning

Related stories

How Language Models Fail: Token-Level Signatures of Committed and Persistent Reasoning Failures

The Consistency Dilemma in LLMs: Generator-Evaluator Agreement and Vulnerability to Mistakes

Self-CTRL: Self-Consistency Training with Reinforcement Learning

Self-Correction Bench: Uncovering and Addressing the Self-Correction Blind Spot in Large Language Models

Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs

Translating Natural Language to Strategic Temporal Specifications via LLMs