Zongyi Li

Yulei Qin, Xiaoyu Tan, Zhengbao He et al.

Reinforcement learning (RL) is the dominant paradigm for sharpening strategic tool use capabilities of LLMs on long-horizon, sparsely-rewarded agent tasks, yet it faces a fundamental challenge of exploration-exploitation trade-off. Existing studies stimulate exploration through the lens of policy entropy, but such mechanical entropy maximization is prone to RL training instability due to the multi-turn distribution shifting. In this paper, we target the progressive exploration-exploitation balance under the guidance of the agent own experiences without succumbing to either entropy collapsing or runaway divergence. We propose SPEAR, a curriculum-based self-imitation learning (SIL) recipe for training agentic LLMs. It extends the vanilla SIL framework, where a replay buffer stores self-generated promising trajectories for off-policy update, by gradually steering the policy evolution within a well-balanced range of entropy across stages. Specifically, our approach incorporates a curriculum to manage the exploration process, utilizing intrinsic rewards to foster skill-level exploration and facilitating action-level exploration through SIL. At first, the auxiliary tool call reward plays a critical role in the accumulation of tool-use skills, enabling broad exposure to the unfamiliar distributions of the environment feedback with an upward entropy trend. As training progresses, self-imitation gets strengthened to exploit existing successful patterns from replayed experiences for comparative action-level exploration, accelerating solution iteration without unbounded entropy growth. To further stabilize training, we recalibrate the advantages of experiences in the replay buffer to address the potential policy drift. Reugularizations such as the clipping of tokens with high covariance between probability and advantage are introduced to the trajectory-level entropy control to curb over-confidence.

Jiayun Wang, Yousuf Aborahama, Arya Khokhar et al.

Photoacoustic computed tomography (PACT) combines optical contrast with ultrasonic resolution, achieving deep-tissue imaging beyond the optical diffusion limit. While three-dimensional PACT systems enable high-resolution volumetric imaging for applications spanning transcranial to breast imaging, current implementations require dense transducer arrays and prolonged acquisition times, limiting clinical translation. We introduce Pano (PACT imaging neural operator), an end-to-end physics-aware model that directly learns the inverse acoustic mapping from sensor measurements to volumetric reconstructions. Unlike existing approaches (e.g. universal back-projection algorithm), Pano learns both physics and data priors while also being agnostic to the input data resolution. Pano employs spherical discrete-continuous convolutions to preserve hemispherical sensor geometry, incorporates Helmholtz equation constraints to ensure physical consistency and operates resolutionindependently across varying sensor configurations. We demonstrate the robustness and efficiency of Pano in reconstructing high-quality images from both simulated and real experimental data, achieving consistent performance even with significantly reduced transducer counts and limited-angle acquisition configurations. The framework maintains reconstruction fidelity across diverse sparse sampling patterns while enabling real-time volumetric imaging capabilities. This advancement establishes a practical pathway for making 3D PACT more accessible and feasible for both preclinical research and clinical applications, substantially reducing hardware requirements without compromising image reconstruction quality.