Papers with Autonomous agents
VisualWebArena: Evaluating Multimodal Agents on Realistic Visual Web Tasks (2024.acl-long)
Copied to clipboard
Jing Yu Koh, Robert Lo, Lawrence Jang, Vikram Duvvur, Ming Lim, Po-Yu Huang, Graham Neubig, Shuyan Zhou, Russ Salakhutdinov, Daniel Fried
| Challenge: | Existing benchmarks focus on text-based agents, neglecting many natural tasks that require visual information to effectively solve. |
| Approach: | They propose a benchmark to assess the performance of multimodal web agents . they use visual and textual inputs to process and interpret natural language instructions . |
| Outcome: | a new benchmark assesses the performance of multimodal agents on visually grounded tasks . the benchmark identifies limitations of text-only agents and offers insights towards building stronger agents for the web . |
AndroidLab: Training and Systematic Benchmarking of Android Autonomous Agents (2025.acl-long)
Copied to clipboard
Yifan Xu, Xiao Liu, Xueqiao Sun, Siyi Cheng, Hao Yu, Hanyu Lai, Shudan Zhang, Dan Zhang, Jie Tang, Yuxiao Dong
| Challenge: | Existing studies on Android agents lack systematic research on open-source and closed-source models. |
| Approach: | They propose a framework for Android agents that includes an operation environment and a reproducible benchmark. |
| Outcome: | The proposed framework lifts the success rate of open-source LLMs and LMMs from 4.59% to 21.50% for LLM and 1.93% to 13.28% for LMM. |
Attacking Vision-Language Computer Agents via Pop-ups (2025.acl-long)
Copied to clipboard
| Challenge: | Existing tools for analyzing and testing VLMs are lacking in understanding what types of attacks are possible and what types are effective. |
| Approach: | They propose to integrate pop-ups into existing agent testing environments to attack VLM agents by ignoring them. |
| Outcome: | The proposed attack success rate is 86% and decreases by 47% when integrating pop-ups into existing agent testing environments. |
DORA: Dynamic Optimization Prompt for Continuous Reflection of LLM-based Agent (2025.coling-main)
Copied to clipboard
| Challenge: | Existing studies have shown that reflection can enhance performance, but our investigation reveals an undesirable pattern in reflection framework: effective self-reflection occurs primarily at the beginning of iterations, with subsequent attempts failing to produce further improvements. |
| Approach: | They propose a framework that generates task-adaptive reflection advice using an external open-source small language model. |
| Outcome: | The proposed framework generates task-adaptive and diverse reflection advice in MiniWoB++ and Alfworld environments. |
The Confidence Dichotomy: Analyzing and Mitigating Miscalibration in Tool-Use Agents (2026.acl-long)
Copied to clipboard
| Challenge: | a fundamental pillar of trustworthiness is calibration, which refers to an agent’s ability to express confidence that reliably reflects its actual performance. |
| Approach: | They propose a reinforcement learning framework that jointly optimizes task accuracy and calibration, supported by a holistic benchmark of reward designs. |
| Outcome: | The proposed framework improves calibration across tool types and shows that trained agents achieve superior calibration and exhibit robust generalization from local training environments to noisy web settings and to distinct domains such as mathematical reasoning. |
xLAM: A Family of Large Action Models to Empower AI Agent Systems (2025.naacl-long)
Copied to clipboard
Jianguo Zhang, Tian Lan, Ming Zhu, Zuxin Liu, Thai Quoc Hoang, Shirley Kokane, Weiran Yao, Juntao Tan, Akshara Prabhakar, Haolin Chen, Zhiwei Liu, Yihao Feng, Tulika Manoj Awalgaonkar, Rithesh R N, Zeyuan Chen, Ran Xu, Juan Carlos Niebles, Shelby Heinecke, Huan Wang, Silvio Savarese, Caiming Xiong
| Challenge: | Autonomous agents powered by large language models (LLMs) have attracted significant research interest, but there are few standards for developing specialized models for agent tasks. |
| Approach: | They propose a series of large action models with dense and mixture-of-expert architectures that unifies, augments, and synthesizes diverse datasets to enhance agent generalizability and performance. |
| Outcome: | The proposed models outperform GPT-4, Claude-3, and many other models in terms of tool use and outperformed GPT-based models on multiple agent ability benchmarks. |
ToolCPT: Improving Tool Utilization in LLM Agents via Continuous Pre-training (2026.findings-acl)
Copied to clipboard
| Challenge: | Current approaches to enhancing tool use for LLM-based agents focus on post-training fine-tuning or test-time context extension. |
| Approach: | They propose to enhance tool knowledge for LLM-based agents during continuous pre-training . they curate 5.1 million code artifacts from large-scale, high-quality code repositories . |
| Outcome: | The proposed model outperforms existing methods on out-of-distribution tools on multiple benchmarks. |