Free Daily Podcast Summary
Daily Paper Cast: Daily Summaries Delivered
by Jingwen Liang, Gengyu Wang
We update every weekday to discuss highest-voted papers from Huggingface Daily Paper. Both the podcast scripts and audio are generated by AI. Creator: Jingwen Liang, 3D ML Gengyu Wang, LLM ML
Latest Episodes
The most recent episodes — sign up to get AI-powered summaries of each one.
- 4 days ago24 min
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
🤗 Upvotes: 105 | cs.CL Authors: Jundong Xu, Qingchuan Li, Jiaying Wu, Yihuai Lan, Shuyue Stella Li, Huichi Zhou, Bowen Jiang, Lei Wang, Jun Wang, Anh Tuan Luu, Caiming Xiong, Hae Won Park, Bryan Hooi, Zhiyuan Hu Title: EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments Arxiv: http://arxiv.org/abs/2606.13681v1 Abstract: Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployment is inherently dynamic, requiring agents to continually align their knowledge, skills, and behavior with changing environments and updated task conditions. To address this gap, we introduce EvoArena, a benchmark suite that models environment changes as sequences of progressive updates across terminal, software, and social domains. We further propose EvoMem, a patch-based memory paradigm that records memory evolution as structured update histories, enabling agents to reason about environmental evolution through changes in their memory. Experiments show that current agents struggle on EvoArena, achieving an average accuracy of 39.6% across evolving terminal, software, and social-preference domains. EvoMem consistently improves performance, yielding an average gain of 1.5% on EvoArena and also improving standard benchmarks such as GAIA and LoCoMo by 6.1% and 4.8%. Beyond individual tasks, EvoMem further improves chain-level accuracy by 3.7% on EvoArena, where success requires completing a consecutive sequence of related evolutionary subtasks. Mechanistic analysis shows that EvoMem improves evidence capture in the memory, indicating better preservation of complete evolving environment states. Our results highlight the importance of modeling evolution in both evaluation and memory for reliable agent deployment.
- 4 days ago26 min
MiniMax Sparse Attention
🤗 Upvotes: 83 | cs.AI Authors: Xunhao Lai, Weiqi Xu, Yufeng Yang, Qiaorui Chen, Yang Xu, Lunbin Zeng, Xiaolong Li, Haohai Sun, Haichao Zhu, Vito Zhang, Pengyu Zhao Title: MiniMax Sparse Attention Arxiv: http://arxiv.org/abs/2606.13392v1 Abstract: Ultra-long-context capability is becoming indispensable for frontier LLMs: agentic workflows, repository-scale code reasoning, and persistent memory all require the model to jointly attend over hundreds of thousands to millions of tokens, yet the quadratic cost of softmax attention makes this untenable at deployment scale. We introduce MiniMax Sparse Attention (MSA), a blockwise sparse attention built upon Grouped Query Attention (GQA). A lightweight Index Branch scores key-value blocks and independently selects a Top-k subset for each GQA group, enabling group-specific sparse retrieval while maintaining efficient block-level execution; the Main Branch then performs exact block-sparse attention over only the selected blocks. Designed around a principle of simplicity and scalability, MSA is deliberately streamlined, making it straightforward to deploy efficiently across a broad range of GPUs. To translate sparsity into practical speedups, we co-design MSA with a GPU execution path that uses exp-free Top-k selection and KV-outer sparse attention to improve tensor-core utilization under block-granular access. On a 109B-parameter model with native multimodal training, MSA performs on par with GQA while reducing per-token attention compute by 28.4x at 1M context. Paired with our co-designed kernel, MSA achieves 14.2x prefill and 7.6x decoding wall-clock speedups on H800. Our inference kernel is available at: https://github.com/MiniMax-AI/MSA. A production-grade natively multimodal model powered by MSA has been publicly released at: https://huggingface.co/MiniMaxAI/MiniMax-M3.
- 4 days ago22 min
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
🤗 Upvotes: 80 | cs.CV, cs.AI Authors: Seokju Cho, Ryo Hachiuma, Abhishek Badki, Hang Su, Byung-Kwan Lee, Chan Hee Song, Sifei Liu, Subhashree Radhakrishnan, Seungryong Kim, Yu-Chiang Frank Wang, Min-Hung Chen Title: SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning Arxiv: http://arxiv.org/abs/2606.13673v1 Abstract: Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-augmented agents attempt to address this by augmenting VLMs with specialist perception modules, yet their effectiveness is bounded by the action interface through which those tools are invoked. In this work, we study how the design of this interface shapes the agent's capacity for open-ended spatial reasoning. Existing spatial agents either employ single-pass code execution, which commits to a full analysis strategy before any intermediate result is observed, or rely on a structured tool-call interface that often offers less flexibility for freely composing operations or tailoring the analysis to each task. Both designs offer limited flexibility for open-ended, complex 3D/4D spatial reasoning. We therefore propose SpatialClaw, a training-free framework for spatial reasoning that adopts code as the action interface. SpatialClaw maintains a stateful Python kernel pre-loaded with input frames and a suite of perception and geometry primitives, letting a VLM-backed agent write one executable cell per step conditioned on all prior outputs, enabling the agent to flexibly compose and manipulate perception results and adapt its analysis to both intermediate text and visual observations and the demands of each problem. Evaluated across 20 spatial reasoning benchmarks spanning a broad range of static and dynamic 3D/4D spatial reasoning tasks, SpatialClaw achieves 59.9% average accuracy, outperforming the recent spatial agent by +11.2 points, with consistent gains across six VLM backbones from two model families without any benchmark- or model-specific adaptation.
- 4 days ago21 min
InterleaveThinker: Reinforcing Agentic Interleaved Generation
🤗 Upvotes: 73 | cs.CV Authors: Dian Zheng, Harry Lee, Manyuan Zhang, Kaituo Feng, Zoey Guo, Ray Zhang, Hongsheng Li Title: InterleaveThinker: Reinforcing Agentic Interleaved Generation Arxiv: http://arxiv.org/abs/2606.13679v1 Abstract: Recent image generators have demonstrated impressive photorealism and instruction-following capabilities in single-image generation and editing. However, constrained by their architectures, they cannot achieve interleaved generation (text-image sequence), which has crucial applications in visual narratives, guidance, and embodied manipulation. Even the latest open-source Unified Multimodal Models (UMMs) exhibit limited performance in this regard. In this paper, we introduce InterleaveThinker, the first multi-agent pipeline designed to endow any existing image generator with interleaved generation capabilities. Specifically, we employ a planner agent to organize the image-text input sequence, instructing the image generator on the required execution at each step. Subsequently, we introduce a critic agent to evaluate the generator's outputs, identify samples that deviate from the planned instructions, and refine the instructions for regeneration. To implement this pipeline, we construct the Interleave-Planner-SFT-80k and Interleave-Critic-SFT-112k to perform a format cold-start. Then we develop Interleave-Critic-RL-13k to reinforce the step-wise instruction correction capability within a generation trajectory using GRPO. Since a single interleaved generation trajectory may involve over 25 generator calls, optimizing the entire trajectory is computationally impractical. Therefore, we propose accuracy reward and step-wise reward, allowing single-step RL to effectively guide the entire generation trajectory. The results show that InterleaveThinker improves performance across various image generators. On interleaved generation benchmarks, it achieves performance comparable to Nano Banana and GPT-5. Surprisingly, it also significantly enhances the base model on reasoning-based benchmarks; for example, on 4-step FLUX.2-klein, we observe substantial gains on WISE and RISE.
- 4 days ago23 min
FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents
🤗 Upvotes: 71 | cs.CL Authors: Jia Deng, Yimeng Chen, Xiaoqing Xiang, Ziyang Zeng, Shuo Tang, Wayne Xin Zhao, Feng Chang, Chuan Hao, Yuan Wei, Ran Tao, Bryan Dai, Ji-Rong Wen Title: FORT-Searcher: Synthesizing Shortcut-Resistant Search Tasks for Training Deep Search Agents Arxiv: http://arxiv.org/abs/2606.12087v1 Abstract: Training deep search agents requires verifiable questions whose answers remain unavailable until sufficient evidence has been acquired through search. Existing synthesis methods often increase apparent difficulty by enriching graph structures, but structural complexity alone does not guarantee realized search difficulty: the intended search process can collapse through a cheaper identifying route. We formalize this gap with a shortcut-aware difficulty framework and identify four actionable shortcut risks: evidence co-coverage, single-clue selectivity, exposed constants, and prior-knowledge binding. To diagnose their realized effects, we use trajectory signatures including solving cost, answer hit time, and prior-shortcut rate. Guided by this framework, we introduce FORT, a Framework of Shortcut-Resistant Training-Data Synthesis. FORT constructs shortcut-resistant training data by controlling shortcut risks across entity selection, evidence graph construction, question formulation, and adversarial refinement. Experiments show that FORT induces longer pre-answer search and fewer shortcut patterns than existing open-source deep search datasets. Using the resulting trajectories, we train FORT-Searcher with supervised fine-tuning (SFT) only, and it achieves the best overall performance among comparable-size open-source search agents on challenging deep search benchmarks. Relevant resources will be made available at https://github.com/RUCAIBox/FORT-Searcher.
- 4 days ago20 min
Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
🤗 Upvotes: 71 | cs.CV, cs.AI, cs.CL Authors: Jiaqi Tang, Jianmin Chen, Youyang Zhai, Wei Wei, Runtao Liu, Mengjie Zhao, Xiangyu Wu, Qingfa Xiao, Qifeng Chen Title: Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding? Arxiv: http://arxiv.org/abs/2606.08063v1 Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in visual understanding, yet their performance degrades significantly under real-world visual corruptions. While existing robustness enhancement approaches exist, they are limited: black-box feature alignment lacks interpretability, and white-box text-based reasoning cannot restore lost pixel-level details. This work investigates a fundamental research question: Can MLLMs recover corrupted visual content by themselves? To address this, we propose Robust-U1, a novel framework that equips MLLMs with explicit visual self-recovery capability for robust understanding. The approach comprises three core stages: supervised fine-tuning for initial reconstruction, reinforcement learning with dual rewards (pixel-level SSIM and semantic-level CLIP similarity) for aligning high visual quality, and multimodal reasoning that jointly considers both the corrupted input and the recovered image. Extensive experiments demonstrate that Robust-U1 achieves state-of-the-art robustness on the real-world corruption benchmark and maintains superior performance under adversarial corruptions on general VQA benchmarks. Analysis confirms that high-quality visual recovery directly enhances reasoning performance, establishing self-recovery as a critical mechanism for robust visual understanding. The source code is available at https://github.com/jqtangust/Robust-U1.
- 4 days ago23 min
MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling
🤗 Upvotes: 69 | cs.LG, cs.AI, cs.CL Authors: Jiacheng Chen, Xinyu Zhang, Shunkai Zhang, Yanmohan Wang, Lin Li, Tiancheng Qin, Qin Wang, Zhengmao Zhu, Tianle Li, Jingyang Li, Zehan Li, Binyang Jiang, Jin Zhu, Han Ding, Fei Yu, Chenyu Du, Zijian Song, Jiayuan Song, Zhi Zhang, Yunan Huang, Weiyu Cheng, Pengyu Zhao, Yu Cheng Title: MaxProof: Scaling Mathematical Proof with Generative-Verifier RL and Population-Level Test-Time Scaling Arxiv: http://arxiv.org/abs/2606.13473v1 Abstract: We present MaxProof, a population-level test-time scaling framework for competition-level mathematical proof in the MiniMax-M3 series. M3 first trains three proof-oriented capabilities -- proof generation, proof verification, and critique-conditioned proof repair -- using a defense-in-depth generative verifier engineered for low false-positive rate. These capabilities are merged into a single released M3 model. At test time, MaxProof treats the model as a generator, verifier, refiner, and ranker, searches over a population of candidate proofs, and returns one final proof through tournament selection. With MaxProof test-time scaling, the M3 model reaches 35/42 on IMO 2025 and 36/42 on USAMO 2026, exceeding the human gold-medal threshold on both.
- 4 days ago20 min
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
🤗 Upvotes: 60 | cs.AI Authors: Wanli Li, Bowen Zhou, Yunyao Yu, Zhou Xu, Yifan Yang, Dongsheng Li, Caihua Shan Title: WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces Arxiv: http://arxiv.org/abs/2606.09426v2 Abstract: Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing benchmarks, however, often evaluate these interfaces as separable capabilities, leaving long-horizon cross-interface orchestration under-tested. Thus, we introduce WeaveBench, a long-horizon hybrid-interface benchmark with 114 tasks across 8 real-world work domains, grounded in real user requests and publicly verifiable artifacts. Each task requires agents to combine GUI observations/actions with CLI/code operations within a single trajectory. We evaluate these tasks on a real Ubuntu desktop inside deployed CLI-agent runtimes, augmented with a minimal desktop-control plugin. We also propose a companion trajectory-aware judge that inspects deliverables, files, screenshots, logs, and action traces, while detecting shortcut behaviors such as fabricated visual evidence or hard-coded metrics. Across frontier model-runtime pairings, the best PassRate reaches only 41.2%, showing the benchmark remains far from saturated. The trajectory-aware judge further reveals that outcome-only grading substantially overestimates agent performance. Overall, WeaveBench exposes a critical gap in CUA evaluation and provides an effective testbed to measure whether agents can orchestrate GUI, CLI, and code operations across long-horizon real-world tasks.
Get Daily Paper Cast summaries in your inbox
Free AI-powered daily recaps. Key takeaways, quotes, and mentions — in a 5-minute read.
Get Free Summaries →Free forever for up to 3 podcasts. No credit card required.
You Might Also Like
Listeners also like.
Latent Space: The AI Engineer Podcast
Covers advances in AI engineering, including foundation models, code generation, and AI agents, through interviews with researchers and developers.
Everyday AI Podcast – An AI and ChatGPT Podcast
Practical AI and ChatGPT tips for professionals to improve productivity and grow their careers.
The AI Daily Brief: Artificial Intelligence News and Analysis
A daily analysis of artificial intelligence news, exploring its creative potential, industry impacts, and ethical challenges.
OpenAI Podcast
Conversations with OpenAI researchers and builders exploring how frontier AI models are developed and used in practice.
"The Cognitive Revolution" | AI Builders, Researchers, and Live Player Analysis
Interviews with AI developers and researchers exploring the transformative impact of artificial intelligence on society and technology.
This Day in AI Podcast
Two friends discuss artificial intelligence, sharing casual insights, personal experiments, and humorous experiences with AI tools and technology.
Google DeepMind: The Podcast
A mathematician explores AI's real-world impact through behind-the-scenes insights from a leading research lab.
Dwarkesh Podcast
Dwarkesh Patel
NVIDIA AI Podcast
Explores how artificial intelligence and emerging technologies drive innovation across science, sustainability, and industry.
The AI XR Podcast.
Industry insiders interview top founders and executives on AI, spatial computing, VR/AR, and synthetic media.
Last Week in AI
Summarizes significant AI news on a weekly basis.
The Anthropic AI Daily Brief
Breaks down Anthropic's latest AI advancements and their real-world implications in clear, accessible language.
About Daily Paper Cast
We update every weekday to discuss highest-voted papers from Huggingface Daily Paper. Both the podcast scripts and audio are generated by AI. Creator: Jingwen Liang, 3D ML Gengyu Wang, LLM ML
Customized Recaps
AI-powered recaps with compact key takeaways, quotes, and insights.
Straight to Your Inbox
Get key takeaways from Daily Paper Cast in a 5-minute read.
Save Hours Every Week
Stay current on your favorite podcasts without falling behind.
Frequently Asked Questions
What is Podzilla's Daily Paper Cast daily summary?
It's a free AI-powered email that summarizes new episodes of Daily Paper Cast as soon as they're published. You get the key takeaways, notable quotes, and links & mentions — all in a quick read.
How does the Daily Paper Cast podcast summary work?
When a new episode drops, our AI transcribes and analyzes it, then generates a personalized summary tailored to your interests and profession. It's delivered to your inbox every morning.
Is this an official Daily Paper Cast product?
No. Podzilla is an independent service that summarizes publicly available podcast content. We're not affiliated with or endorsed by Jingwen Liang, Gengyu Wang.
Can I get summaries of other podcasts too?
Absolutely! The free plan covers up to 3 podcasts. Upgrade to Pro for 15, or Premium for 50. Browse our full catalog at /podcasts.
How often does Daily Paper Cast release new episodes?
Daily Paper Cast publishes daily. Our AI generates a summary within hours of each new episode.
What topics does Daily Paper Cast cover?
Daily Paper Cast covers topics including Science, Technology. Our AI identifies the specific themes in each episode and highlights what matters most to you.
Start getting Daily Paper Cast summaries tomorrow morning.
Free forever for up to 3 podcasts. No credit card required.
Free forever for up to 3 podcasts. No credit card required.