- EO-1: An Open Unified Embodied Foundation Model for General Robot Control
Delin Qu, Haoming Song, Qizhi Chen, Zhaoqing Chen, Xianqiang Gao · Aug 28, 2025
Long Horizon
The human ability to seamlessly perform multimodal reasoning and physical interaction in the open world is a core goal for general purpose embodied intelligent systems.
- NPG-Muse: Scaling Long Chain-of-Thought Reasoning with NP-Hard Graph Problems
Yuyao Wang, Bowen Liu, Jianheng Tang, Nuo Chen, Yuhan Li · Aug 28, 2025
However, developing these Long CoT behaviors relies heavily on post-training with high-quality datasets, which are typically costly and human-curated (e.g., mathematics and code), leaving scalable alternatives unexplored.
- Diffusion Language Models Know the Answer Before Decoding
Pengxiang Li, Yefan Zhou, Dilxat Muhtar, Lu Yin, Shilin Yan · Aug 27, 2025
Empirical evaluations of LLaDA-8B and Dream-7B across multiple tasks show that Prophet reduces the number of decoding steps by up to 3.4x while preserving high generation quality.
- Your AI Bosses Are Still Prejudiced: The Emergence of Stereotypes in LLM-Based Multi-Agent Systems
Jingyu Guo, Yingying Xu · Aug 27, 2025
Multi Agent
While stereotypes are well-documented in human social interactions, AI systems are often presumed to be less susceptible to such biases.
- Language and Experience: A Computational Model of Social Learning in Complex Tasks
Cédric Colas, Tracey Mills, Ben Prystawski, Michael Henry Tessler, Noah Goodman · Aug 26, 2025
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments.
- Hybrid Deep Searcher: Scalable Parallel and Sequential Search Reasoning
Dayoon Ko, Jihyuk Kim, Haeju Park, Sohyeon Kim, Dahyun Lee · Aug 26, 2025
Long Horizon
Large reasoning models (LRMs) combined with retrieval-augmented generation (RAG) have enabled deep research agents capable of multi-step reasoning with external knowledge retrieval.
- Why Synthetic Isn't Real Yet: A Diagnostic Framework for Contact Center Dialogue Generation
Rishikesh Devanathan, Varun Nathan, Ayush Kumar · Aug 25, 2025
In this work, we benchmark multiple generation strategies guided by structured supervision on call attributes (Intent Summaries, Topic Flows, and Quality Assurance (QA) Forms) across multiple languages.
- Classification errors distort findings in automated speech processing: examples and solutions from child-development research
Lucas Gautheron, Evan Kidd, Anton Malko, Marvin Lavechin, Alejandrina Cristia · Aug 21, 2025
With the advent of wearable recorders, scientists are increasingly turning to automated methods of analysis of audio and video data in order to measure children's experience, behavior, and outcomes, with a sizable literature employing long-
- HebID: Detecting Social Identities in Hebrew-language Political Text
Guy Mor-Lan, Naama Rivlin-Angert, Yael R. Kaplan, Tamir Sheafer, Shaul R. Shenhav · Aug 21, 2025
We benchmark multilabel and single-label encoders alongside 2B-9B-parameter generative LLMs, finding that Hebrew-tuned LLMs provide the best results (macro-$F_1$ = 0.74).
- Tokens with Meaning: A Hybrid Tokenization Approach for Turkish
M. Ali Bayram, Ali Arda Fincan, Ahmet Semih Gümüş, Sercan Karakaş, Banu Diri · Aug 19, 2025
We further validate practical utility with downstream sentence embedding benchmarks under a strict \emph{random initialization} control to isolate tokenizer inductive bias.
- Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Dongchun Xie · Aug 19, 2025
Reinforcement Learning with Verifiable Reward (RLVR) has emerged as a powerful paradigm for unlocking reasoning capabilities in large language models, yet its full potential is hindered by two under-explored dimensions: Depth-the hardest pr
- TASER: Table Agents for Schema-guided Extraction and Recommendation
Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso · Aug 18, 2025
Critique Edit
To address this, we present TASER (Table Agents for Schema-guided Extraction and Recommendation), a continuously learning, agentic table extraction system that converts highly unstructured, multi-page, heterogeneous tables into normalized,
- SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh · Aug 18, 2025
Reliable uncertainty estimation is a key missing piece for on-device monitoring in TinyML: microcontrollers must detect failures, distribution shift, or accuracy drops under strict flash/latency budgets, yet common uncertainty approaches (d
- CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures
Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin · Aug 16, 2025
Pairwise Preference Multi Agent
Game-theoretic interactions between agents with Large Language Models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been sufficiently quantified.
- UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles
Akshat Dubey, Aleksandar Anžel, Bahar İlgen, Georges Hattab · Aug 13, 2025
Explainable Artificial Intelligence (XAI) techniques, such as SHapley Additive exPlanations (SHAP), have become essential tools for interpreting complex ensemble tree-based models, especially in high-stakes domains such as healthcare analyt
- 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning
Wenkai Li, Liwen Sun, Zhenxiang Guan, Xuhui Zhou, Maarten Sap · Aug 11, 2025
Multi Agent
We introduce a multi-agent framework that decomposes privacy reasoning into specialized subtasks (extraction, classification), reducing the information load on any single agent while enabling iterative validation and more reliable adherence
- Position: Beyond Sensitive Attributes, ML Fairness Should Quantify Structural Injustice via Social Determinants
Zeyu Tang, Alex John London, Atoosa Kasirzadeh, Sarah Stewart de Ramirez, Peter Spirtes · Aug 10, 2025
Algorithmic fairness research has largely framed unfairness as discrimination along sensitive attributes.
- SQL-Exchange: Transforming SQL Queries Across Domains
Mohammadreza Daviran, Brian Lin, Davood Rafiei · Aug 9, 2025
Our comprehensive evaluation across multiple model families and benchmark datasets -- assessing structural alignment with source queries, execution validity on target databases, and semantic correctness -- demonstrates that SQL-Exchange is
- Seeing Through the Noise: Improving Infrared Small Target Detection and Segmentation from Noise Suppression Perspective
Maoxun Yuan, Duanni Meng, Ziteng Xi, Tianyi Zhao, Shiji Zhao · Aug 9, 2025
Infrared small target detection and segmentation (IRSTDS) is a critical yet challenging task in defense and civilian applications, owing to the dim, shapeless appearance of targets and severe background clutter.
- Not All Errors Are Created Equal: ASCoT Addresses Late-Stage Fragility in Efficient LLM Reasoning
Dongxu Zhang, Ning Yang, Yiding Sun, Jihua Zhu, Jinnan Yang · Aug 7, 2025
While Chain-of-Thought (CoT) prompting empowers Large Language Models (LLMs), ensuring reasoning reliability remains an open challenge.
- Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning
Magauiya Zhussip, Dmitriy Shopkhoev, Ammar Ali, Stamatios Lefkimmiatis · Aug 6, 2025
Experiments across scales (100M-700M parameters) show that MASA achieves better benchmark accuracy and perplexity than GQA, low-rank baselines and recent Repeat-all-over/Sequential sharing at comparable parameter budgets.
- CoAct-1: Computer-using Multi-Agent System with Coding Actions
Linxin Song, Yutong Dai, Viraj Prabhu, Jieyu Zhang, Taiwei Shi · Aug 5, 2025
Long Horizon
Autonomous agents that operate computers via Graphical User Interfaces (GUIs) often struggle with efficiency and reliability on complex, long-horizon tasks.
- Hidden Dynamics of Massive Activations in Transformer Training
Jorge Gallego-Feliciano, S. Aaron McClendon, Juan Morinelli, Stavros Zervoudakis, Antonios Saravanos · Aug 5, 2025
We present the first comprehensive analysis of massive activation development throughout transformer training, using the Pythia model family as our testbed, and release our full dataset publicly to support further research.
- RooseBERT: A New Deal For Political Language Modelling
Deborah Dore, Elena Cabrio, Serena Villata · Aug 5, 2025
The increasing amount of political debates and politics-related discussions calls for the definition of novel computational methods to automatically analyse such content with the final goal of lightening up political deliberation to citizen
- When Algorithms Meet Artists: Semantic Compression of Artists' Concerns in the Public AI-Art Debate
Ariya Mukherjee-Gandhi, Oliver Muellerklein · Aug 5, 2025
Artists occupy a paradoxical position in generative AI: their work trains the models reshaping creative labor.
- PoeTone: A Framework for Constrained Generation of Structured Chinese Songci with LLMs
Zhan Qu, Shuzhou Yuan, Michael Färber · Aug 4, 2025
We first develop a comprehensive, multi-faceted evaluation framework that includes: (i) a formal conformity score, (ii) automated quality assessment using LLMs, (iii) human evaluation, and (iv) classification-based probing tasks.
- MolReasoner: Toward Effective and Interpretable Reasoning for Molecular LLMs
Guojiang Zhao, Zixiang Lu, Yutang Ge, Sihang Li, Zheng Cheng · Aug 4, 2025
Extensive evaluations demonstrate that MolReasoner significantly outperforms a wide range of strong baselines in both molecule generation and captioning tasks.
- Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning
Xinting Huang, Michael Hahn · Aug 3, 2025
Understanding internal representations of neural models is a core interest of mechanistic interpretability.
- LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
Guozhao Mo, Wenliang Zhong, Jiawei Chen, Qianhao Yuan, Xuanang Chen · Aug 3, 2025
Tool Use
Unfortunately, there is still a large gap between real-world MCP usage and current evaluation: they typically assume single-server settings and directly inject tools into the model's context, bypassing the challenges of large-scale retrieva
