activity
20242026
collaborators

9 papers

cs.CL2026

ATLAS: All-round Testing of Long-context Abilities across Scales

Deli Huang, Cunguang Wang, Hongyin Tang +15

Long-context language models now advertise context windows up to millions of tokens, yet evaluations typically report a single length or a narrow task family, masking two failure m…

cs.AI2026

Bridging the Detection-to-Abstention Gap in Reasoning Models under Insufficient Information

Renjie Gu, Jiaxu Li, Yihao Wang +8

We highlight a failure mode of large reasoning models on questions with insufficient information: models may recognize that a problem is under-specified, yet still continue reasoni…

cs.PL2026

Skill-as-Pseudocode: Refactoring Skill Libraries to Pseudocode for LLM Agents

Xinze Li, Yuhang Zang, Yixin Cao +1

Markdown skill libraries for LLM agents ship as free-form prose, forcing the agent to re-derive both the input schema and the concrete invocation syntax on every retrieval. We obse…

cs.CL2026

EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents

Xinze Li, Ziyue Zhu, Siyuan Liu +4

We introduce EMemBench, a programmatic benchmark for evaluating long-term memory of agents through interactive games. Rather than using a fixed set of questions, EMemBench generate…

cs.IR2025

Towards Storage-Efficient Visual Document Retrieval: An Empirical Study on Reducing Patch-Level Embeddings

Yubo Ma, Jinsong Li, Yuhang Zang +8

Despite the strong performance of ColPali/ColQwen2 in Visualized Document Retrieval (VDR), it encodes each page into multiple patch-level embeddings and leads to excessive memory u…

cs.CL2024

Long Context vs. RAG for LLMs: An Evaluation and Revisits

Xinze Li, Yixin Cao, Yubo Ma +1

Extending context windows (i.e., Long Context, LC) and using retrievers to selectively access relevant information (i.e., Retrieval-Augmented Generation, RAG) are the two main stra…