arXiv AI July 28, 2026 By Junyi Zou

Adapter Merging Reactivates Latent Reasoning Traces: A Mechanism Analysis

arXiv:2601. 18350v5 Announce Type: replace-cross Abstract: Large language models fine-tuned via a two-stage pipeline (domain adaptation followed by instruction alignment) can exhibit non-trivial interference after adapter merging, including the re-emergence of explicit reasoning traces under strict decoding.

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

arXiv AI

Jul 10

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

arXiv:2607. 08393v1 Announce Type: new Abstract: Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks.

By Lu Dai, Ziyang Rao, Yili Wang, Hanqing Wang, Hao Liu, Hui Xiong

llms fine-tuning

arXiv AI

Jul 22

Fluid Reasoning Representations

arXiv:2602. 04843v2 Announce Type: replace Abstract: Frontier large language models increasingly solve complex tasks involving abstract concepts through extended test-time thinking.

By Dmitrii Kharlapenko, Terry Jingchen Zhang, Arth Singh, Alessandro Stolfo, Arthur Conmy, Mrinmaya Sachan, Zhijing Jin

llms

arXiv Machine Learning

Jun 5

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

arXiv:2606. 05680v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the automatic synthesis (generation) of register-transfer level (RTL) code from natural language instructions, offering a promising pathway to accelerate chip design.

By Mohammad Akyash, Nowfel Mashnoor, Kimia Azar, Hadi Kamali

llms rag agents fine-tuning safety

arXiv AI

Jun 9

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

arXiv:2606. 07808v1 Announce Type: new Abstract: Reasoning language models deployed in agentic workflows must follow an instruction hierarchy: when instructions from different sources conflict, the model should obey the highest-privilege applicable instruction.

By Sanjay Kariyappa, G. Edward Suh

llms agents benchmarks

arXiv AI

Jun 4

The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation

arXiv:2606. 04057v1 Announce Type: cross Abstract: Large language models (LLMs) now generate substantial production code, often for tasks with multiple valid algorithmic solutions.

By Akanksha Narula, Mofasshara Binte Rafique, Laurent Bindschaedler

llms benchmarks

arXiv Machine Learning

Jun 5

Reasoning Models Don't Just Think Longer, They Move Differently

arXiv:2605. 15454v2 Announce Type: replace-cross Abstract: Reasoning-trained language models often spend more tokens on harder problems, but longer chains of thought do not show whether a model is merely computing for more steps or following a different internal trajectory.

By Anders Gj{\o}lbye, Lars Kai Hansen, Sanmi Koyejo

llms

Related stories

Towards Mechanistically Understanding Why Memorized Knowledge Fails to Generalize in Large Language Model Finetuning

Fluid Reasoning Representations

CASS-RTL: Correctness-Aware Subspace Steering for RTL Generation with LLMs

Where Instruction Hierarchy Breaks: Diagnosing and Repairing Failures in Reasoning Language Models

The Invisible Lottery: How Subtle Cues Steer Algorithm Choice in LLM Code Generation

Reasoning Models Don't Just Think Longer, They Move Differently