Berkeley AI Research

Adaptive Parallel Reasoning: The Next Paradigm in Efficient Inference Scaling

apr-fig { text-align: center; margin: 1. 35em 0; line-height: 1.

Berkeley AI Research

Jul 26

Teaching LLMs to Update Beliefs for Efficient Long-Horizon Interaction

abbel-fig { display: block; text-align: center; margin: 2. 4em 0; line-height: 1.

llms agents nlp reinforcement-learning fine-tuning efficiency benchmarks

Berkeley AI Research

Apr 20

Gradient-based Planning for World Models at Longer Horizons

grasp-results-table table { font-size: 0. 875rem; line-height: 1.

llms diffusion computer-vision reinforcement-learning robotics safety

Berkeley AI Research

Nov 1, 2025

RL without TD learning

In this post, I’ll introduce a reinforcement learning (RL) algorithm based on an “alternative” paradigm: divide and conquer . Unlike traditional methods, this algorithm is not based on temporal difference (TD) learning (which has scalability challenges ), and scales well to long-horizon tasks.

llms reinforcement-learning robotics benchmarks

arXiv AI

Jul 7

Correlation-Weighted Multi-Reward Optimization for Compositional Generation

arXiv:2603. 18528v2 Announce Type: replace Abstract: Text-to-image models produce images that align well with natural language prompts, but compositional generation has long been a central challenge.

By Jungmyung Wi, Hyunsoo Kim, Donghyun Kim

diffusion benchmarks

arXiv AI

Aug 7

CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation

arXiv:2603. 08652v2 Announce Type: replace Abstract: Recent advancements in Unified Multimodal Models (UMMs) have significantly advanced text-to-image (T2I) generation, particularly through the integration of Chain-of-Thought (CoT) reasoning.

By Haodong Li, Chunmei Qing, Huanyu Zhang, Dongzhi Jiang, Yihang Zou, Hongbo Peng, Dingming Li, Yuhong Dai, ZePeng Lin, Juanxi Tian, Yi Zhou, Siqi Dai, Jingwei Wu, Pheng-Ann Heng

diffusion multimodal

arXiv AI

4d ago

VISOR: Agentic Visual Retrieval-Augmented Generation via Iterative Search and Over-horizon Reasoning

arXiv:2604. 09508v2 Announce Type: replace-cross Abstract: Visual Retrieval-Augmented Generation (VRAG) empowers Vision-Language Models to retrieve and reason over visually rich documents.

By Yucheng Shen, Jiulong Wu, Jizhou Huang, Dawei Yin, Lingyong Yan, Min Cao

llms rag agents reinforcement-learning efficiency multimodal benchmarks

Simon Willison

Aug 10

Introducing Muse Glimmer

Introducing Muse Glimmer Meta are back in the open weights game! Muse Glimmer is a brand new 30B model under a clean Apache 2.

llms agents benchmarks

arXiv AI

Aug 3

M3MAD-Bench: Multi-Dimensional Evaluation of Multi-Agent Debate Across Domains and Modalities

arXiv:2601. 02854v2 Announce Type: replace Abstract: As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning.

By Ao Li, Jinghui Zhang, Luyu Li, Yuxiang Duan, Lang Gao, Mingcai Chen, Weijun Qin, Shaopeng Li, Fengxian Ji, Ning Liu, Lizhen Cui, Xiuying Chen, Yuntao Du

agents multimodal benchmarks safety

arXiv AI

Jul 3

ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models

arXiv:2512. 07843v2 Announce Type: replace-cross Abstract: Scaling inference-time computation has enabled Large Language Models (LLMs) to achieve strong reasoning performance, but their inherently sequential decoding incurs substantial latency, motivating parallelization of the generation process.

By Long Lian, Sida Wang, Felix Juefei-Xu, Tsu-Jui Fu, Xiuyu Li, Adam Yala, Trevor Darrell, Alane Suhr, Yuandong Tian, Xi Victoria Lin

llms reinforcement-learning fine-tuning efficiency benchmarks

Google AI Blog

Mar 14, 2024

Cappy: Outperforming and boosting large multi-task language models with a small scorer

Posted by Yun Zhu and Lijuan Liu, Software Engineers, Google Research Large language model (LLM) advancements have led to a new paradigm that unifies various natural language processing (NLP) tasks within an instruction-following framework. This paradigm is exemplified by recent multi-task LLMs, such as T0 , FLAN , and OPT-IML .

By Google AI

llms nlp reinforcement-learning fine-tuning safety

arXiv Machine Learning

Jun 25

SyncLoop: A Multimodal Dual-Loop Framework for Self-Improving Mathematical Reasoning

arXiv:2507. 16518v3 Announce Type: replace-cross Abstract: Recent advances in multimodal large language models (MLLMs) have shown impressive reasoning capabilities.

By Xiuwei Chen, Wentao Hu, Hanhui Li, Yongxin Wang Jun Zhou, Zisheng Chen, Meng Cao, Yihan Zeng, Kui Zhang, Yu-Jie Yuan, Jianhua Han, Hang Xu, Xiaodan Liang

llms reinforcement-learning fine-tuning multimodal benchmarks

arXiv Machine Learning

Jul 27

Multi-Agent Debate and Visual Information Extraction for SeePhys Pro: A 1st-Place Technical Report from ICML 2026 AI4Math Track 3 Challenge

arXiv:2607. 21946v1 Announce Type: new Abstract: This technical report presents our approach to Challenge Track~3: SeePhys Pro at the 3rd AI for Math Workshop, where the task is to answer college-level physics questions whose statement and figure may be given partly or entirely as an image.

By Jiseok Kwak, Suhyeon Jo, Taewoo Kim, Yeongmin Kim, Byeonghu Na, Il-chul Moon

llms agents benchmarks

Related stories