6 papers
DeepLoop: Depth Scaling for Looped Transformers
Shuzhen Li, Yifan Zhang, Jiacheng Guo +2
Looped Transformers scale sequential computation by applying a compact stack of physical blocks for multiple rounds, increasing unrolled depth without increasing stored parameters.…
Interactive Benchmarks
Baoqing Yue, Zihan Zhu, Yutong Han +6
Existing reasoning evaluation paradigms suffer from different limitations: fixed benchmarks are increasingly saturated and vulnerable to contamination, while preference-based evalu…
Deep Delta Learning
Yifan Zhang, Yifeng Liu, Mengdi Wang +1
Transformer residual streams evolve through additive updates. Although a sufficiently expressive residual block can represent content replacement, standard architectures do not par…
Web World Models
Jichen Feng, Yifan Zhang, Chenggong Zhang +3
Language agents increasingly require persistent worlds in which they can act, remember, and learn. Existing approaches sit at two extremes: conventional web frameworks provide reli…
Monadic Context Engineering
Yifan Zhang, Yang Yuan, Mengdi Wang +1
The proliferation of Large Language Models (LLMs) has catalyzed a shift towards autonomous agents capable of complex reasoning and tool use. However, current agent architectures ar…
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
Jiacheng Guo, Suozhi Huang, Zixin Yao +16
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in t…