Hanlin Wang

Hanlin Wang, Chak Tou Leong, Jian Wang et al.

Language models are exhibiting increasing capability in knowledge utilization and reasoning. However, when applied as agents in embodied environments, they often suffer from misalignment between their intrinsic knowledge and environmental knowledge, leading to infeasible actions. Traditional environment alignment methods, such as supervised learning on expert trajectories and reinforcement learning, encounter limitations in covering environmental knowledge and achieving efficient convergence, respectively. Inspired by human learning, we propose Exploration-based Error Correction Learning (E2CL), a novel framework that leverages exploration-induced errors and environmental feedback to enhance environment alignment for embodied agents. E2CL incorporates teacher-guided and teacher-free explorations to gather environmental feedback and correct erroneous actions. The agent learns to provide feedback and self-correct, thereby enhancing its adaptability to target environments. Extensive experiments in the VirtualHome environment demonstrate that E2CL-trained agents outperform those trained by baseline methods and exhibit superior self-correction capabilities.

Hanlin Wang, Chak Tou Leong, Jiashuo Wang et al.

Reinforcement learning (RL) holds significant promise for training LLM agents to handle complex, goal-oriented tasks that require multi-step interactions with external environments. However, a critical challenge when applying RL to these agentic tasks arises from delayed rewards: feedback signals are typically available only after the entire task is completed. This makes it non-trivial to assign delayed rewards to earlier actions, providing insufficient guidance regarding environmental constraints and hindering agent training. In this work, we draw on the insight that the ultimate completion of a task emerges from the cumulative progress an agent makes across individual steps. We propose Stepwise Progress Attribution (SPA), a general reward redistribution framework that decomposes the final reward into stepwise contributions, each reflecting its incremental progress toward overall task completion. To achieve this, we train a progress estimator that accumulates stepwise contributions over a trajectory to match the task completion. During policy optimization, we combine the estimated per-step contribution with a grounding signal for actions executed in the environment as the fine-grained, intermediate reward for effective agent training. Extensive experiments on common agent benchmarks (including Webshop, ALFWorld, and VirtualHome) demonstrate that SPA consistently outperforms the state-of-the-art method in both success rate (+2.5\% on average) and grounding accuracy (+1.9\% on average). Further analyses demonstrate that our method remarkably provides more effective intermediate rewards for RL training. Our code is available at https://github.com/WangHanLinHenry/SPA-RL-Agent.

Hanlin Wang, Jian Wang, Chak Tou Leong et al.

Large language model (LLM)-based agents have shown promise in tackling complex tasks by interacting dynamically with the environment. Existing work primarily focuses on behavior cloning from expert demonstrations or preference learning through exploratory trajectory sampling. However, these methods often struggle to address long-horizon tasks, where suboptimal actions accumulate step by step, causing agents to deviate from correct task trajectories. To address this, we highlight the importance of timely calibration and the need to automatically construct calibration trajectories for training agents. We propose Step-Level Trajectory Calibration (STeCa), a novel framework for LLM agent learning. Specifically, STeCa identifies suboptimal actions through a step-level reward comparison during exploration. It constructs calibrated trajectories using LLM-driven reflection, enabling agents to learn from improved decision-making processes. We finally leverage these calibrated trajectories with successful trajectories for reinforced training. Extensive experiments demonstrate that STeCa significantly outperforms existing methods. Further analysis highlights that timely calibration enables agents to complete tasks with greater robustness. Our code and data are available at https://github.com/WangHanLinHenry/STeCa.

Taosha Fan, Hanlin Wang, Michael Rubenstein et al.

In this paper, we consider the problem of planar graph-based simultaneous localization and mapping (SLAM) that involves both poses of the autonomous agent and positions of observed landmarks. We present CPL-SLAM, an efficient and certifiably correct algorithm to solve planar graph-based SLAM using the complex number representation. We formulate and simplify planar graph-based SLAM as the maximum likelihood estimation (MLE) on the product of unit complex numbers, and relax this nonconvex quadratic complex optimization problem to convex complex semidefinite programming (SDP). Furthermore, we simplify the corresponding complex semidefinite programming to Riemannian staircase optimization (RSO) on the complex oblique manifold that can be solved with the Riemannian trust region (RTR) method. In addition, we prove that the SDP relaxation and RSO simplification are tight as long as the noise magnitude is below a certain threshold. The efficacy of this work is validated through applications of CPL-SLAM and comparisons with existing state-of-the-art methods on planar graph-based SLAM, which indicates that our proposed algorithm is capable of solving planar graph-based SLAM certifiably, and is more efficient in numerical computation and more robust to measurement noise than existing state-of-the-art methods. The C++ code for CPL-SLAM is available at https://github.com/MurpheyLab/CPL-SLAM.