arXiv AI

SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation

SimSkill is a self‑evolving large‑language‑model agent designed for the SUMO traffic simulator. It continuously detects capability gaps, creates and solves environment‑grounded tasks, verifies solutions via an action–critic loop, and stores experiences in episodic, procedural, and semantic memory. Evaluations on two held‑out benchmarks across three LLM backbones show up to a 25‑percentage‑point improvement in verified success, with procedural and semantic memory contributing complementarily.

arXiv AI
Sep 4

SimSkill: A Lifelong Learning AI Agent for Autonomous Mastery of Traffic Simulation

SimSkill is a lifelong learning AI agent that uses the SUMO traffic simulator to autonomously identify gaps in its capabilities, generate and solve tasks grounded in the environment, and verify solutions through an action‑critic loop. It consolidates experience into episodic, procedural, and semantic memory without updating its backbone language model, creating a reusable library for traffic‑simulation workflows. Evaluations on two benchmarks with three different LLM backbones show that SimSkill can improve verified completion rates by up to 25 percentage points, with procedural and semantic memory contributing complementarily to performance.

By Qi Liu, Qinzheng Wang, Yiming Bie
arXiv AI
Jun 2

TrafficClaw: A Generalizable LLM Agent in the Unified Physical Environment for Urban Traffic Control

arXiv:2604. 17456v2 Announce Type: replace Abstract: Large language model (LLM) agents have shown strong capabilities in long-horizon reasoning, tool use, and decision-making in digital environments, yet extending them to physically grounded systems remains challenging.

By Siqi Lai, Pan Zhang, Yuping Zhou, Jindong Han, Yansong Ning, Hao Liu
arXiv AI
Jul 15

TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale

arXiv:2607. 13028v1 Announce Type: cross Abstract: Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains.

By Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang, Zachary Lee, Tim Wang, Wei Zhan
arXiv AI
Aug 20

SPADE: Self-Play in Adaptive Synthetic Executable Environments

SPADE (Self-Play in Adaptive Synthetic Executable Environments) is a reinforcement‑learning framework where a single large language model acts as both an Environment Designer—creating executable, long‑horizon training environments—and a Reasoning Agent—learning to act within those environments. The framework uses a regret signal based on the difference between rewarded performance with and without privileged hints to guide the Designer toward environments that are challenging yet solvable. Experiments show that, when scaled to 30‑billion‑parameter models, SPADE outperforms fixed‑environment baselines by significant margins across math, science, code, and reasoning benchmarks, and improves tool‑use performance on BFCL‑v4 and ACEBench‑Agent. whyItMatters":"By making environment design a learnable component, SPADE enables continuous self‑improvement and demonstrates that adaptive, self‑generated training environments can substantially boost language‑model performance across diverse tasks."

By Bo Liu, Simon Yu, Yiding Jiang, Ao Qu, Andrew Zhao, Zichen Liu, Junsu Kim, Zijian Zhou, Seungone Kim, Tongzheng Ren, Mickel Liu, Hanfei Yu, Zhaorun Chen, Weiyan Shi, Paul Pu Liang, Luke Zettlemoyer, Yejin Choi, Natasha Jaques
arXiv AI
Jun 30

Hierarchical Experimentalist Agents

arXiv:2606. 29315v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to take actions in the real world and support human decision-making, yet most agents rely on parametric knowledge, fixed post-training data, retrieval, or search.

By Abhranil Chandra, Sankaran Vaidyanathan, Utsav Dhanuka, Varun Gandhi, Scott Niekum
arXiv AI
Jul 13

Improving Language Agents through BREW: Bootstrapping expeRientially-learned Environmental knoWledge

arXiv:2511. 20297v2 Announce Type: replace Abstract: Large Language Model (LLM)-based agents are increasingly capable of complex, multi-step tasks such as GUI automation, tool use, and data manipulation, yet they cannot learn from experience: each new session rediscovers solutions from scratch.

By Shashank Kirtania, Param Biyani, Priyanshu Gupta, Yasharth Bajpai, Roshni Iyer, Sumit Gulwani, Gustavo Soares
arXiv Computer Vision
Aug 25

BehaviorWorldGen: Closing the Loop between Action Models and World Simulators via Controllable Behavior-Aware Structured World Generation

arXiv:2608.22187v1 Announce Type: cross Abstract: Modern driving action models are increasingly improved in a self-improvement loop, where a learned world simulator imagines future observations and t...

By Jiaqi Wang, Zhuo Zhang, Haining Guan, Tingguang Zhou, Haowen Cui, Zhongyang Zhu, Yulong Zheng, ChuanYe Wang, Xuefeng Chen, Zhen Yang, Tianchen Deng, Feiyang Tan, Hangning Zhou, Bo Dai, Lixia Shen, Xiwu Chen, Xiyang Wang, Jiajun Zhu
arXiv AI
Sep 10

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

The paper introduces Procedural Graphs, a framework that structures procedural knowledge for large language model agents as (procedure, relation, procedure) triplets, analogous to knowledge graphs for factual data. At each decision point, a guidance model uses the local subgraph to bias the agent’s next action, while an LLM refiner self‑evolves the graph by comparing failed and successful trajectories, editing its topology to improve performance. Experiments across various datasets, tasks, and LLMs show that Procedural Graphs consistently outperform memory‑based baselines, and the self‑evolution mechanism further enhances results without manual engineering.

By Yuxing Lu, Yicheng Chen, Shanchan Wu, Sercan \"{O}. Ar{\i}k