Long chain-of-thought (CoT) reasoning models such as DeepSeek-R1 keep lengthening their inference chains under test-time scaling, yet standard self-attention incurs quadratic cost in context length, making long-CoT deployment costly in production. We therefore introduce LISA (Linear-Indexed Sparse Attention), a plug-an...
Yu Zhao, Zekun Zhang, Fan Jiang et al.· 0 citations
Existing LLM logical-reasoning benchmarks largely focus on object-level inference under fixed predicates and rules, leaving higher-order reasoning over rules and policies underexplored. We introduce HOLogicBench, a 1,379-instance benchmark that systematically evaluates five representative higher-order reasoning operati...
Yucheng Wu, Jundong Xu, Mingzhen Ju et al.· 0 citations
Modern AI agents are increasingly capable of routine financial-analysis tasks such as retrieving documents and updating spreadsheets. A harder challenge is forecasting an unknown future from incomplete information. Public markets provide a natural testbed: analysts routinely predict discrete events with information fro...
Mahesh Ramesh, Eric Cho, Alice Lu et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
In video calls and livestreamed discussions, recognizing speakers' emotions helps identify emotionally salient segments and supports fine-grained video content analysis. Multimodal Emotion Recognition in Conversation (ERC) provides an approach to recognizing emotions in such content by integrating textual, visual, and...
Linan Zhu, Zihao Zhai, Mengfei Xu et al.· 0 citations
The emergence of multi-agent systems introduces novel moderation challenges that extend beyond content filtering. Agents with $\textit{malicious intent}$ may contribute content that appears benign to evade content-based moderation, while serving a hidden objective. To address this challenge, we introduce Bot-Mod a mode...
Ali Al-Lawati, Nafis Tripto, Abolfazl Ansari et al.· 0 citations
These findings establish that (self- or human-supervised) feedback-based trajectory optimization is a principled methodology for mitigating plan-execution gaps in autonomous agent systems.
Tuo Zhang, A. Popa, Yan Xu et al.· arXiv.org· 5 citations
Distilling long reasoning traces from a teacher model into a smaller student also passes on the teacher's reasoning habits. Prior work and our annotation of teacher traces show that current reasoning models often start without a plan, verify superficially, abandon promising solution paths, and take unchecked shortcuts....
Ik-hwan Kim, Hyeongrok Han, Mingi Jung et al.· 0 citations
Recent advancements in Large Reasoning Models (LRMs), exemplified by DeepSeek-R1, have underscored the potential of scaling inference-time compute through Group Relative Policy Optimization (GRPO). However, GRPO frequently suffers from gradient signal attenuation when encountering problems that are either too trivial o...
Yu Zhao, Fan Jiang, Tianle Liu et al.· 0 citations
Large language models (LLMs) have demonstrated abilities to perform complex tasks in multiple domains, including mathematical and scientific reasoning. In this work, we construct a novel agent framework for solving representative problems in scientific computing. The proposed agent incorporates a "rewriting-resolution-...
This paper presents HiMA-Ecom, a hierarchical multi-agent benchmark for e-commerce assistants with 22.8K instances, and presents HiMA-R1, a hierarchical multi-agent benchmark for e-commerce assistants, pairing agent-specific supervised fine-tuning data with system-level supervision for end-to-end multi-agent reinforcem...
Jun-Xing Hu, Ai Han, Haolan Zhan et al.· 8 citations· ⚡1
Estimation error in machine learning prognostic models can propagate into poor maintenance decisions. We study a data-driven predictive maintenance problem coupling health-condition estimation with a joint ordering-replacement model. We show that the conventional Estimate-Then-Optimize (ETO) approach yields inconsisten...
