AI Agent

Controlling Large Language Model with Latent Actions

Chengxing Jia, Ziniu Li, Pengyuan Wang, Yi-Chen Li, Zhenyu Hou, Yuxiao Dong, Yang Yu

专题命中 Agent评测 ：agent(abstract)；分类 cs.CL、cs.LG

Mobile-MMLU: A Mobile Intelligence Language Understanding Benchmark

Sondos Mahmoud Bsharat, Mukul Ranjan, Aidar Myrzakhan, Jiacheng Liu, Bowei Guo, Shengkun Tang, Zhuang Liu, Yuanzhi Li, Zhiqiang Shen

专题命中 Agent评测 ：planning(abstract)；分类 cs.AI、cs.CL

Comments An order-invariant and mobile-centric benchmark. Code and data are available at: https://github.com/VILA-Lab/Mobile-MMLU

Probabilistic Shielding for Safe Reinforcement Learning

Edwin Hamel-De le Court, Francesco Belardinelli, Alexander W. Goodall

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 13 pages, 3 figures, Conference: AAAI 2025

Open Models, Closed Minds? On Agents Capabilities in Mimicking Human Personalities through Open Large Language Models

Lucio La Cava, Andrea Tagarelli

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Comments Accepted and presented at the AAAI 2025 Conference. CHANGES in version v2: (i) Enhanced methodology and evaluation based on BFI in addition to MBTI, with expanded set of LLM agents; (ii) author list changed w.r.t. version (v1), see Acknowledgements

EnvBench: A Benchmark for Automated Environment Setup

Aleksandra Eliseeva, Alexander Kovrigin, Ilia Kholkin, Egor Bogomolov, Yaroslav Zharov

专题命中 Agent评测 ：agentic(abstract)；分类 cs.LG、cs.SE

Comments Accepted at the DL4Code workshop at ICLR'25

Counterfactual Realizability

Arvind Raghavan, Elias Bareinboim

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments published at ICLR'25 (spotlight)

An LLM-Based Approach for Insight Generation in Data Analysis

Alberto Sánchez Pérez, Alaa Boukhary, Paolo Papotti, Luis Castejón Lozano, Adam Elwood

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Comments Accepted for publication at NAACL 2025

Multi-Task Reinforcement Learning Enables Parameter Scaling

Reginald McLean, Evangelos Chatzaroulas, Jordan Terry, Isaac Woungang, Nariman Farsad, Pablo Samuel Castro

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

HASARD: A Benchmark for Vision-Based Safe Reinforcement Learning in Embodied Agents

Tristan Tomilin, Meng Fang, Mykola Pechenizkiy

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Accepted to ICLR 2025

Toward Stable World Models: Measuring and Addressing World Instability in Generative Environments

Soonwoo Kwon, Jin-Young Kim, Hyojun Go, Kyungjune Baek

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Preprint

Provable Zero-Shot Generalization in Offline Reinforcement Learning

Zhiyong Wang, Chen Yang, John C. S. Lui, Dongruo Zhou

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 30 pages, 1 figure, 1 table

Less is more? Rewards in RL for Cyber Defence

Elizabeth Bates, Chris Hicks, Vasilios Mavroudis

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 4 Pages

Adaptive Active Inference Agents for Heterogeneous and Lifelong Federated Learning

Anastasiya Danilenka, Alireza Furutanpey, Victor Casamayor Pujol, Boris Sedlak, Anna Lackinger, Maria Ganzha, Marcin Paprzycki, Schahram Dustdar

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 12 pages, double column, 17 figures, 2 tables

This Is Your Doge, If It Please You: Exploring Deception and Robustness in Mixture of LLMs

Lorenz Wolf, Sangwoong Yoon, Ilija Bogunovic

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 35 pages, 9 figures, 16 tables

InDRiVE: Intrinsic Disagreement based Reinforcement for Vehicle Exploration through Curiosity Driven Generalized World Model

Feeza Khan Khanzada, Jaerock Kwon

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments This work has been submitted to IROS 2025 and is currently under review

EchoQA: A Large Collection of Instruction Tuning Data for Echocardiogram Reports

Lama Moukheiber, Mira Moukheiber, Dana Moukheiiber, Jae-Woo Ju, Hyung-Chul Lee

专题命中 Agent评测 ：AI agent(abstract)；分类 cs.AI、cs.CL

Comments NeurIPS SafeGenAI 2024

ExpertPrompting: Instructing Large Language Models to be Distinguished Experts

Benfeng Xu, An Yang, Junyang Lin, Quan Wang, Chang Zhou, Yongdong Zhang, Zhendong Mao

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Mapping representations in Reinforcement Learning via Semantic Alignment for Zero-Shot Stitching

Antonio Pio Ricciardi, Valentino Maiorca, Luca Moschella, Riccardo Marin, Emanuele Rodolà

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 11 pages, 3 figures, 2 tables

From Overfitting to Robustness: Quantity, Quality, and Variety Oriented Negative Sample Selection in Graph Contrastive Learning

Adnan Ali, Jinlong Li, Huanhuan Chen, Ali Kashif Bashir

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

AutoAdvExBench: Benchmarking autonomous exploitation of adversarial example defenses

Nicholas Carlini, Javier Rando, Edoardo Debenedetti, Milad Nasr, Florian Tramèr

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Acquiring Grounded Representations of Words with Situated Interactive Instruction

Shiwali Mohan, Aaron H. Mininger, James R. Kirk, John E. Laird

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Journal ref Advances in Cognitive Systems (2012)

An Extensive Evaluation of PDDL Capabilities in off-the-shelf LLMs

Kaustubh Vyas, Damien Graux, Sébastien Montella, Pavlos Vougiouklis, Ruofei Lai, Keshuang Li, Yang Ren, Jeff Z. Pan

专题命中 Agent评测 ：planning(abstract)；分类 cs.AI、cs.CL

Comments Under review

SDPO: Segment-Level Direct Preference Optimization for Social Agents

Aobo Kong, Wentao Ma, Shiwan Zhao, Yongbin Li, Yuchuan Wu, Ke Wang, Xiaoqian Liu, Qicheng Li, Yong Qin, Fei Huang

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Strategic Classification With Externalities

Safwan Hossain, Evi Micha, Yiling Chen, Ariel Procaccia

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Brain-Model Evaluations Need the NeuroAI Turing Test

Jenelle Feather, Meenakshi Khosla, N. Apurva Ratan Murty, Aran Nayebi

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments 9 pages, 4 figures, 2 tables

Speaking the Right Language: The Impact of Expertise Alignment in User-AI Interactions

Shramay Palta, Nirupama Chandrasekaran, Rachel Rudinger, Scott Counts

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Comments arXiv Version

EgoSocialArena: Benchmarking the Social Intelligence of Large Language Models from a First-person Perspective

Guiyang Hou, Wenqi Zhang, Yongliang Shen, Zeqi Tan, Sihao Shen, Weiming Lu

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 14 pages, 6 figures

Exploring Sentiment Manipulation by LLM-Enabled Intelligent Trading Agents

David Byrd

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

A Socratic RAG Approach to Connect Natural Language Queries on Research Topics with Knowledge Organization Systems

Lew Lefton, Kexin Rong, Chinar Dankhara, Lila Ghemri, Firdous Kausar, A. Hannibal Hamdallahi

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.CL

Comments 6 pages, 2 figures, AAAI 2025 Workshop on A Translational Institute for Knowledge Axiomatization

DistRL: An Asynchronous Distributed Reinforcement Learning Framework for On-Device Control Agents

Taiyi Wang, Zhihao Wu, Jianheng Liu, Jianye Hao, Jun Wang, Kun Shao

专题命中 Agent评测 ：agent(abstract)；分类 cs.AI、cs.LG

Comments Paper and Appendix, 26 pages