Tootfinder

Q&A with researcher Petter Törnberg on his pre-print study showing how social media's structural architecture creates problematic outcomes like echo chambers (Jennifer Ouellette/Ars Technica)
https://arstechnica.com/science/2025/08/study-social-medi…

Study: Social media probably can’t be fixed
“The [structural] mechanism producing these problematic outcomes is really robust and hard to resolve.”…

Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
Zetian Sun, Dongfang Li, Zhuoen Chen, Yuhuai Qin, Baotian Hu
https://arxiv.org/abs/2508.10548 https://…

Stabilizing Long-term Multi-turn Reinforcement Learning with Gated Rewards
Reward sparsity in long-horizon reinforcement learning (RL) tasks remains a significant challenge, while existing outcome-based reward shaping struggles to define meaningful immediate rewards without introducing bias or requiring explicit task decomposition. Alternatively, verification-based reward shaping uses stepwise critics, but misalignment between immediate rewards and long-term objectives can lead to reward hacking and suboptimal policies. In this work, we address this problem in the con…

SSRL: Self-Search Reinforcement Learning
Yuchen Fan, Kaiyan Zhang, Heng Zhou, Yuxin Zuo, Yanxu Chen, Yu Fu, Xinwei Long, Xuekai Zhu, Che Jiang, Yuchen Zhang, Li Kang, Gang Chen, Cheng Huang, Zhizhou He, Bingning Wang, Lei Bai, Ning Ding, Bowen Zhou
https://arxiv.org/abs/2508.10874

SSRL: Self-Search Reinforcement Learning
We investigate the potential of large language models (LLMs) to serve as efficient simulators for agentic search tasks in reinforcement learning (RL), thereby reducing dependence on costly interactions with external search engines. To this end, we first quantify the intrinsic search capability of LLMs via structured prompting and repeated sampling, which we term Self-Search. Our results reveal that LLMs exhibit strong scaling behavior with respect to the inference budget, achieving high pass@k …

While the Brazilian government is selling off the Amazon Rainforest to fossil fuel companies, banks like Banco Santander are bankrolling them to further destroy the Amazon. Without money, fossil fuel giants can’t drill. Sign the petition and tell Santander, stop destroying the Amazon! https://act.350.org/sign/Santander-ama

Tell Santander: Stop destroying the Amazon!
While the Brazilian government is selling off the Amazon Rainforest to fossil fuel companies, banks like Banco Santander are bankrolling them to further destroy the Amazon. Without money, fossil fuel giants can’t drill. Sign the petition and tell Santander, stop destroying the Amazon!

A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering
Chenliang Zhang, Lin Wang, Yuanyuan Lu, Yusheng Qi, Kexin Wang, Peixu Hou, Wenshi Chen
https://arxiv.org/abs/2508.10337

A Curriculum Learning Approach to Reinforcement Learning: Leveraging RAG for Multimodal Question Answering
This paper describes the solutions of the Dianping-Trust-Safety team for the META CRAG-MM challenge. The challenge requires building a comprehensive retrieval-augmented generation system capable for multi-modal multi-turn question answering. The competition consists of three tasks: (1) answering questions using structured data retrieved from an image-based mock knowledge graph, (2) synthesizing information from both knowledge graphs and web search results, and (3) handling multi-turn conversati…

UI-Venus Technical Report: Building High-performance UI Agents with RFT
Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, Yue Wen, Jingya Dou, Fei Tang, Jinzhen Lin, Yulin Liu, Zhenlin Guo, Yichen Gong, Heng Jia, Changlong Gao, Yuan Guo, Yong Deng, Zhenyu Guo, Liang Chen, Weiqiang Wang

UI-Venus Technical Report: Building High-performance UI Agents with RFT
We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous …

Inpainting-Guided Policy Optimization for Diffusion Large Language Models
Siyan Zhao, Mengchen Liu, Jing Huang, Miao Liu, Chenyu Wang, Bo Liu, Yuandong Tian, Guan Pang, Sean Bell, Aditya Grover, Feiyu Chen
https://arxiv.org/abs/2509.10396

Inpainting-Guided Policy Optimization for Diffusion Large Language Models
Masked diffusion large language models (dLLMs) are emerging as promising alternatives to autoregressive LLMs, offering competitive performance while supporting unique generation capabilities such as inpainting. We explore how inpainting can inform RL algorithm design for dLLMs. Aligning LLMs with reinforcement learning faces an exploration challenge: sparse reward signals and sample waste when models fail to discover correct solutions. While this inefficiency affects LLMs broadly, dLLMs offer a…

Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
Chuyuan Li, Austin Xu, Shafiq Joty, Giuseppe Carenini
https://arxiv.org/abs/2509.09852 h…

Topic-Guided Reinforcement Learning with LLMs for Enhancing Multi-Document Summarization
A key challenge in Multi-Document Summarization (MDS) is effectively integrating information from multiple sources while maintaining coherence and topical relevance. While Large Language Models have shown impressive results in single-document summarization, their performance on MDS still leaves room for improvement. In this paper, we propose a topic-guided reinforcement learning approach to improve content selection in MDS. We first show that explicitly prompting models with topic labels enhanc…

Arintra, whose AI medical coding system translates clinical documentation into insurance codes for healthcare providers, raised a $21M Series A led by Peak XV (Erin Brodwin/Axios)
https://www.axios.com/pro/health-tech-deals/2025/08/12/arintra-21m…

Exclusive: Arintra raises $21M to expand into denials prevention
As financial pressure mounts on U.S. health systems, Arintra aims to leverage gen-AI to secure reimbursement while reducing dependency on human coders.

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Ahmed Masry, Abhay Puri, Masoud Hashemi, Juan A. Rodriguez, Megh Thakkar, Khyati Mahajan, Vikas Yadav, Sathwik Tejaswi Madhusudhan, Alexandre Pich\'e, Dzmitry Bahdanau, Christopher Pal, David Vazquez, Enamul Hoque, Perouz Taslakian, Sai Rajeswar, Spandana Gella
https://

BigCharts-R1: Enhanced Chart Reasoning with Visual Reinforcement Finetuning
Charts are essential to data analysis, transforming raw data into clear visual representations that support human decision-making. Although current vision-language models (VLMs) have made significant progress, they continue to struggle with chart comprehension due to training on datasets that lack diversity and real-world authenticity, or on automatically extracted underlying data tables of charts, which can contain numerous estimation errors. Furthermore, existing models only rely on supervise…