arXiv AI

Implicit Rule Induction with Test-Time Task Embeddings in ARC-like Tasks

The paper introduces a two‑step test‑time training protocol, Embed‑TTT, for Vision ARC (VARC) that first fine‑tunes only the task embedding and then fine‑tunes the backbone. This approach consistently produces task embeddings that better align with the underlying rules, improves retrieval and linear probing, and recovers the geometric structure of parametric rules. Even fine‑tuning only the tiny embedding component solves a significant portion of ARC‑AGI‑1, ConceptARC, and Mini‑ARC tasks, while the full two‑step pipeline further enhances performance and demonstrates compositional rule interpolation.

arXiv AI

Sep 24

PotARCin: Multi-Dimensional Evaluation of Skill Acquisition in Abstract Reasoning Tasks

PotARCin expands the ARC benchmark by evaluating abstract reasoning across five dimensions—Definition, Classification, Constrained Generation, Editing, and Inversion—using programmatic generation of new task instances. The study shows a 25‑52 percentage‑point performance gap between standard ARC evaluation and PotARCin, and reveals that multi‑dimensional assessment can reorder models that appear equivalent under single‑metric accuracy. Additionally, a new held‑out set, P‑ARC, demonstrates low model accuracy (1‑8%) across all dimensions, highlighting the need for more comprehensive tests of abstract reasoning.

By Claas Beger, Ryan Yi, Melanie Mitchell

benchmarks

arXiv AI

Jun 26

\textsc{DiARC}: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models

arXiv:2606. 26530v1 Announce Type: cross Abstract: The Abstraction and Reasoning Corpus (ARC;~\citealp{chollet2019measure}) contains tasks that require summarizing patterns from limited grid samples and predicting output grids.

By Yuxuan Yang, Feiyang Li, Yile Wang

llms fine-tuning benchmarks safety

arXiv AI

Aug 12

Loop, Think, & Generalize: Implicit Reasoning in Recurrent-Depth Transformers

arXiv:2604. 07822v2 Announce Type: replace-cross Abstract: We study implicit reasoning, i.

By Harsh Kohli, Srinivasan Parthasarathy, Huan Sun, Yuekun Yao

llms

arXiv AI

Jun 29

DiARC: Distinguishing Positive and Negative Samples Helps Improving ARC-like Reasoning Ability of Large Language Models

arXiv:2606. 26530v2 Announce Type: replace-cross Abstract: The Abstraction and Reasoning Corpus (ARC) contains tasks that require summarizing patterns from limited grid samples and predicting output grids.

By Yuxuan Yang, Feiyang Li, Yile Wang

llms fine-tuning benchmarks safety

arXiv Computer Vision

Sep 1

LaME: Learning to Think in Latent Space for Multimodal Embedding via Information Bottleneck

arXiv:2606.13061v3 Announce Type: replace Abstract: Reasoning-driven universal multimodal embedding has advanced rapidly by introducing Chain-of-Thought (CoT) reasoning into the embedding pipeline. D...

By Peixi Wu, Biao Yang, Feipeng Ma, Bosong Chai, Bo Lin, Wei Yuan, Fan Yang, Tingting Gao, Hebei Li, Xiaoyan Sun

rag diffusion efficiency multimodal

arXiv AI

Sep 1

Zipping the Thought: When and How Compressed Reasoning Data Works in LLM Post-Training

The paper investigates how different forms of compressed chain‑of‑thought (CoT) reasoning—Explicit, Composed, and Implicit—affect large language model (LLM) performance after supervised fine‑tuning (SFT). Using a synthetic compositional reasoning task, the authors show that coarser CoT requires more SFT data, that Composed and Implicit CoT benefit more from data scaling (with Composed also benefiting from repetition), and that reinforcement learning with verifiable rewards (RLVR) can decompose compressed steps learned during SFT. Additionally, unidirectional CoT ordering improves generalization on longer sequential tasks.

By Kohsei Matsutani, Gouki Minegishi, Takeshi Kojima, Yusuke Iwasawa, Yutaka Matsuo

llms reinforcement-learning fine-tuning

arXiv AI

Jun 8

DyCon: Dynamic Reasoning Control via Evolving Difficulty Modeling

arXiv:2606. 07108v1 Announce Type: new Abstract: Recent advances in Large Reasoning Models (LRMs) demonstrate remarkable performance improvements by iteratively reflecting, exploring, and executing complex tasks, yet suffer from inefficiencies due to redundant reasoning, known as "overthinking".

By Tengyao Tu, Yulin Li, Hui-Ling Zhen, Libo Qin, Zhoujun Wei, Jinghua Piao, Zhuotao Tian, Yong Li, Min Zhang

rag nlp benchmarks

arXiv Computer Vision

Aug 28

Reason in the Words You Speak: Idiolectal Paraphrasing Off-Policy Traces for Reasoning Distillation in VideoLLMs

The paper introduces Echo-GRPO, a method that rewrites privileged reasoning traces into a model’s own idiolect to align off‑policy supervision with the student policy’s vocabulary. By preserving semantics through Dual‑Reference Decoding, Echo‑GRPO mitigates gradient clipping on critical reasoning tokens and improves reasoning distillation. The approach is instantiated as VideoEcho‑R1 for video reasoning, yielding consistent gains across multiple multimodal LLM backbones and benchmarks, and it can be applied as a plug‑in to both RL and supervised fine‑tuning frameworks.

By Ji Soo Lee, Jinyoung Park, Seohyun Lee, Jongha Kim, Joonmyung Choi, Jinsung Yoon, Hyunwoo J. Kim

llms reinforcement-learning fine-tuning efficiency multimodal benchmarks

arXiv AI

Sep 15

Reason What Matters: Retrieval-Grounded Reasoning for Universal Multimodal Embeddings

arXiv:2609.15296v1 Announce Type: new Abstract: Universal multimodal embedding (UME) learns unified representations across modalities, enabling a single model to support diverse retrieval tasks. Rece...

By Mingzhou Jiang, Peixi Wu, Hang Cheng, Yunhao Zhou, Biao Yang, Wei Yuan, Yun Li, Fan Yang, Wenwu Ou, Honghui He

rag efficiency multimodal benchmarks

arXiv AI

Jul 1

From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators

arXiv:2606. 30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutions often lack the structural consistency needed for reliable deployment.

By Gan Luo, Zihan Qin, Bin Dong, Wotao Yin

llms nlp reinforcement-learning fine-tuning benchmarks

arXiv AI

Sep 16

Thinking Deeper, Not Longer: Memory-Efficient Test-Time Reasoning with Depth-Recurrent Transformers for Compositional Generalization

arXiv:2603.21676v2 Announce Type: replace-cross Abstract: Standard Transformers have a fixed computational depth, limiting their ability to generalize to tasks that require variable-depth reasoning....

By Hung-Hsuan Chen

llms safety

arXiv Computation and Language

Sep 1

REER-PT: Reverse-Engineered Reasoning for Perplexity-Guided Pre-training Data Augmentation

arXiv:2608.30627v1 Announce Type: new Abstract: As language-model compute continues to scale, high-quality training data is becoming an increasingly important bottleneck. Conventional next-token pred...

By Haoran Que, Jiajun Shi, Ting Huang, Renming Pang, Jiaheng Liu, Ge Zhang, Wenhao Huang, Shen Yan, Wei Ye, Shikun Zhang

benchmarks

Related stories