Papers with action selection
MobileCity: An Efficient Framework for Large-Scale Urban Behavior Simulation (2026.eacl-industry)
Copied to clipboard
| Challenge: | Existing methods for simulating realistic urban behaviors rely on static profiles and synchronous inference pipelines that hinder scalability. |
| Approach: | They propose a lightweight generative agent framework for city-scale simulation powered by cognitively-grounded generative agents. |
| Outcome: | Experiments with 4,000 agents show that MobileCity generates more human-like urban dynamics than baselines while maintaining high computational efficiency. |
Interactive Text Games: Lookahead Is All You Need! (2025.acl-srw)
Copied to clipboard
| Challenge: | Existing approaches to ground LLMs in textual interactions have been limited due to low computational efficiency and limited performance. |
| Approach: | They propose to use Lookahead models to ground LLMs in interactive text-based games to investigate their language grounding capabilities. |
| Outcome: | The proposed model significantly improves training speed and performance relative to the size of the action space. |
LEAP & LEAN: Look-ahead Planning and Agile Navigation for LLM Agents (2025.acl-industry)
Copied to clipboard
| Challenge: | Existing approaches to train large-scale models with extensive datasets are limited by their inadequate planning capabilities compared to humans. |
| Approach: | They propose a paradigm that enhances the performance of Large Language Models (LLMs) they use look-ahead planning to refine action selection and LEAN to streamline navigation through agile prompt construction. |
| Outcome: | The proposed framework outperforms agents trained via imitation learning, reinforcement learning, and reasoning-based approaches without any fine-tuning. |
DiffG-RL: Leveraging Difference between Environment State and Common Sense (2022.findings-emnlp)
Copied to clipboard
| Challenge: | Existing approaches to solving text-based games require background knowledge as the context is important. |
| Approach: | They propose a novel agent that organizes environment states and common sense by interactive objects with a dedicated graph encoder. |
| Outcome: | The proposed agent outperforms baselines in text-based games by 17% of scores. |
GAMEBoT: Transparent Assessment of LLM Reasoning in Games (2025.acl-long)
Copied to clipboard
| Challenge: | Existing efforts to create benchmarks that move beyond superficial pattern recognition to delve into the profound reasoning skills required for problemsolving face challenges such as insufficient interpretability, performance saturation or data contamination. |
| Approach: | They propose a gaming arena designed for rigorous assessment of LLM reasoning capabilities. |
| Outcome: | The proposed framework decomposes complex reasoning into predefined modular subproblems and generates ground truth for these subproblem types. |
WebEvolver: Enhancing Web Agent Self-Improvement with Co-evolving World Model (2025.emnlp-main)
Copied to clipboard
| Challenge: | Agent self-improvement, where agents train their underlying Large Language Model (LLM) on self-sampled trajectories, shows promising results but often stagnates in web environments due to limited exploration and under-utilization of pretrained web knowledge. |
| Approach: | They propose a co-evolving Large Language Model (LLM) that predicts the next observation based on current observation and action within the web environment. |
| Outcome: | The proposed framework shows that agents can perform better in real-world web environments without using any distillation from more powerful close-sourced models. |
Structured Preference Optimization for Vision-Language Long-Horizon Task Planning (2025.emnlp-main)
Copied to clipboard
Xiwen Liang, Min Lin, Weiqi Ruan, Rongtao Xu, Yuecheng Liu, Jiaqi Chen, Bingqian Lin, Yuzheng Zhuang, Xiaodan Liang
| Challenge: | Existing vision-language planning methods struggle with long-horizon reasoning in dynamic environments due to the difficulty of training models to generate high-quality reasoning processes. |
| Approach: | They propose a framework that enhances reasoning and action selection for long-horizon task planning through structured evaluation and optimized training. |
| Outcome: | The proposed framework outperforms existing methods on short-horizon tasks but struggles with long-horizon reasoning in dynamic environments. |
World Modeling Makes a Better Planner: Dual Preference Optimization for Embodied Task Planning (2025.acl-long)
Copied to clipboard
| Challenge: | Existing approaches focus on action selection or use pre-trained models as world models to enhance planning capabilities. |
| Approach: | They propose a new learning framework that optimizes state prediction and action selection through preference learning. |
| Outcome: | The proposed method outperforms existing methods and GPT-4o on VoTa-Bench and Qwen2-VL (7B), LLaVA-1.6 (7B) and LLama-3.2 (11B). |