paper-with-me

홈 › Papers

AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts

2026-01-28 · Shicheng Fang, Yuxin Wang, Xiaoran Liu, Jiahao Lu, Chuanyuan Tan, Xinchi Chen, Yining Zheng, Xuanjing Huang, Xipeng Qiu arxiv

The evolution of Large Language Models (LLMs) into autonomous agents necessitates the management of extensive, dynamic contexts. Current benchmarks, however, remain largely static, relying on passive retrieval tasks that fail to simulate the complexities of agent-environment interaction, such as non-linear reasoning and iterative feedback. To address this, we introduce \textbf{AgentLongBench}, which evaluates agents through simulated environment rollouts based on Lateral Thinking Puzzles. This framework generates rigorous interaction trajectories across knowledge-intensive and knowledge-free scenarios. Experiments with state-of-the-art models and memory systems (32K to 4M tokens) expose a critical weakness: while adept at static retrieval, agents struggle with the dynamic information synthesis essential for workflows. Our analysis indicates that this degradation is driven by the minimum number of tokens required to resolve a query. This factor explains why the high information density inherent in massive tool responses poses a significantly greater challenge than the memory fragmentation typical of long-turn dialogues.

📄 PDF Abstract BibTeX arXiv:2601.20730

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

GSM-Infinite: How Do Your LLMs Behave over Infinitely Increasing Context Length and Reasoning Complexity?

2025-02-07 · Yang Zhou, Hongyi Liu, Zhuoming Chen, Yuandong Tian 외

Long-context large language models (LLMs) have recently shown strong performance in information retrieval and long-document QA. However, to tackle the most challenging intellectual problems, LLMs must reason effectively …

8kInformation RetrievalMath

3D-RPE: Enhancing Long-Context Modeling Through 3D Rotary Position Encoding

2024-06-14 · Xindian Ma, Wenyuan Liu, Peng Zhang, Nan Xu

Inspired by the Bloch Sphere representation, we propose a novel rotary position encoding on a three-dimensional sphere, named 3D Rotary Position Encoding (3D-RPE). 3D-RPE is an advanced version of the widely used 2D Rota…

Language ModelingLanguage ModellingNatural Language UnderstandingPosition

MemLong: Memory-Augmented Retrieval for Long Text Modeling

2024-08-30 · Weijie Liu, Zecheng Tang, Juntao Li, Kehai Chen 외

Recent advancements in Large Language Models (LLMs) have yielded remarkable success across diverse fields. However, handling long contexts remains a significant challenge for LLMs due to the quadratic time and space comp…

4kDecoderGPUInformation Retrieval+4

KVMem: Virtualizing Million-Token Agent Workspaces on a Consumer GPU

2026-09-04 · Di Chai, Leye Wang, Zeshen Su, Zhiguo Xia 외 arxiv

Modern LLM agents operate in persistent workspaces whose accumulated history can exceed both GPU KV capacity and the model's native context window. Existing systems typically compact older context into summaries or retri…

$\infty$Bench: Extending Long Context Evaluation Beyond 100K Tokens

2024-02-21 · Xinrong Zhang, Yingfa Chen, Shengding Hu, Zihang Xu 외

Processing and reasoning over long contexts is crucial for many practical applications of Large Language Models (LLMs), such as document comprehension and agent construction. Despite recent strides in making LLMs process…