8 papers
Agents' Last Exam
Yiyou Sun, Xinyang Han, Weichen Zhang +378
Recent AI systems have achieved strong results on a wide range of benchmarks, yet these gains have not translated into economically meaningful deployment across many professional d…
Beyond Semantic Organization: Memory as Execution State Management for Long-Horizon Agents
Yaoqi Chen, Haibin Lai, Yuru Feng +12
LLM-based agents increasingly tackle long-horizon tasks with interdependent decisions, where each action reshapes future constraints and intermediate errors can cascade. Existing R…
Reasoning Matters: Mitigate Hallucination in Multimodal Large Reasoning Models via Reasoning-Conditioned Preference Optimization
Jiawei Kong, Hao Fang, Shunxiang Liao +5
Multimodal Large Reasoning Models introduce the reasoning paradigm, demonstrating strong capabilities on complex vision-language tasks. However, they still suffer from severe hallu…
Heterogeneous Parallelism for Multimodal Large Language Model Training
Yashaswi Karnati, Kamran Jafari, Akash Mehra +10
Foundation model training is becoming multimodal, from post-training pipelines to large-scale pretraining. As modality coverage broadens, context windows grow, and encoder LLM scal…
Gating and Learnable Temperature for Graph Attention Mechanisms
Zhongtian Ma, Hao Wu, Yexin Zhang +3
Graph attention networks learn neighbor importance through data-dependent coefficients, but standard layers lack explicit control over unreliable feature dimensions and use fixed s…
HabitatAgent: An End-to-End Multi-Agent System for Housing Consultation
Hongyang Yang, Yanxin Zhang, Yang She +5
Housing selection is a high-stakes and largely irreversible decision problem. We study housing consultation as a decision-support interface for housing selection. Existing housing…
World Models for Policy Refinement in StarCraft II
Yixin Zhang, Ziyi Wang, Yiming Rong +6
Large Language Models (LLMs) have recently shown strong reasoning capabilities, motivating their use in complex decision-making environments. StarCraft II (SC2), with its massive s…
Step-3 is Large yet Affordable: Model-system Co-design for Cost-effective Decoding
StepFun, :, Bin Wang +195
Large language models (LLMs) face low hardware efficiency during decoding, especially for long-context reasoning tasks. This paper introduces Step-3, a 321B-parameter VLM with hard…