A Unified Framework for Document Parsing Tasks
[Submitted on 17 Dec 2024 (v1), last revised 22 May 2025 (this version, v2)] View a PDF of the paper ...
Read more
Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
[Submitted on 21 Mar 2025 (v1), last revised 22 May 2025 (this version, v2)] View a PDF of the paper ...
Read more
Impacts on Evaluation of LMs
[Submitted on 18 Feb 2025 (v1), last revised 21 May 2025 (this version, v2)] View a PDF of the paper ...
Read more
[2410.13779] The Mystery of the Pathological Path-star Task for Language Models
[Submitted on 17 Oct 2024 (v1), last revised 19 May 2025 (this version, v2)] View a PDF of the paper ...
Read more
General-Purpose Dual-Agent Framework for Reliable Reasoning on Knowledge Graphs
[Submitted on 18 Feb 2025 (v1), last revised 20 May 2025 (this version, v5)] View a PDF of the paper ...
Read more
Can Embodied Agents Understand Vague Human Instructions in Task Planning?
[Submitted on 16 May 2025 (v1), last revised 19 May 2025 (this version, v2)] View a PDF of the paper ...
Read more
LLM-KG-Bench 3.0: A Compass for SemanticTechnology Capabilities in the Ocean of LLMs
arXiv:2505.13098v1 Announce Type: cross Abstract: Current Large Language Models (LLMs) can assist developing program code beside many other things, but ...
Read more
LLM Agent as a Shield between User and Recommender Systems
[Submitted on 20 Feb 2025 (v1), last revised 16 May 2025 (this version, v2)] View a PDF of the paper ...
Read more
Towards a Deeper Understanding of Reasoning Capabilities in Large Language Models
arXiv:2505.10543v1 Announce Type: cross Abstract: While large language models demonstrate impressive performance on static benchmarks, the true potential of large ...
Read more
Superposition Yields Robust Neural Scaling
arXiv:2505.10465v1 Announce Type: cross Abstract: The success of today’s large language models (LLMs) depends on the observation that larger models ...
Read more
