7 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…
Self-Distilled Policy Gradient
Yifeng Liu, Shiyuan Zhang, Yifan Zhang +1
On-policy self-distillation, where a language model conditions on privileged context to supervise its own generations, is a promising source of dense supervision for sparse-reward…
MOSAIC: Efficient Mixture-of-Agent Scheduling via Adaptive Aggregation and Inference Concurrency
Saptarshi Mitra, Yifan Zhang, Rachid Karami +5
Mixture-of-Agents (MoA) systems improve reasoning accuracy by routing each query to multiple expert LLMs and aggregating their outputs. Efficiently executing this workload on limit…
Does Unification Come at a Cost? Uni-SafeBench: A Safety Benchmark for Unified Multimodal Large Models
Zixiang Peng, Yongxiu Xu, Qin-Yi Zhang +5
Unified Multimodal Large Models (UMLMs) integrate understanding and generation capabilities within a single architecture. While unified architectures expand multimodal capabilities…
Execution-Verified Reinforcement Learning for Optimization Modeling
Runda Guan, Xiangqing Shen, Jiajun Zhang +3
Automating optimization modeling with LLMs is a promising path toward scalable decision intelligence, but existing approaches either rely on agentic pipelines built on closed-sourc…
MiroThinker: Pushing the Performance Boundaries of Open-Source Research Agents via Model, Context, and Interactive Scaling
MiroMind Team, Song Bai, Lidong Bing +52
We present MiroThinker v1.0, an open-source research agent designed to advance tool-augmented reasoning and information-seeking capabilities. Unlike previous agents that only scale…
From Harm to Help: Turning Reasoning In-Context Demos into Assets for Reasoning LMs
Haonan Wang, Weida Liang, Zihang Fu +8
Recent reasoning LLMs (RLMs), especially those trained with verifier-based reinforcement learning, often perform worse with few-shot CoT than with direct answering. We revisit this…