arXiv subjects

Xiaoxuan Peng

Publications and source records attributed to Xiaoxuan Peng.

4 recordsLinked to original sources

arXiv2026

Atria Dawn: The Dawn of Agentic Superintelligence

As AI agents become participants in the development of their successors, they reshape both the production of intelligence and the role of human researchers. We introduce Atria Dawn Preview, a foundation agentic language model designed for scientific research and engineering workflows, with the goal of expanding the frontier of agent productivity in the real world. This model is trained via a Verifiable Experience Pipeline that connects tool-mediated interactions to executable environments and externally verified outcomes. Across 16 benchmarks spanning real-world research, engineering, and digital work, Atria Dawn Preview is competitive with frontier agents and achieves the highest reported score on five of them. Beyond standalone performance, we examine the real research-and-development process behind this model as a case study of human--AI collaboration, analyzing 769 task records from 56 participants together with agent logs. When asked to evaluate completed tasks under comparable conditions, participants rated about one-third of completed AI-assisted tasks as infeasible without AI. More strikingly, agents frequently propose methods and implement revisions, while humans retain most final decisions and guide exploration through judgment and feedback. These observations indicate a shift from task-level execution to project-level partnership, with human effort concentrating on what is worth pursuing and how evidence should guide research. Progress toward more autonomous AI research must therefore advance both the capacity for discovery and the capacity for meaningful human oversight, preserving accountable human authority over the risks and direction of continued development.

cs.AI↗

arXiv2026

LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents

Mastering terminal environments requires language agents capable of multi-step planning, feedback-grounded execution, and dynamic state adaptation. However, training such agents is currently bottlenecked by a reliance on scraped external repositories, which limits domain diversity, environment controllability, and the targeting of specific capability deficits. We introduce LiteCoder-Terminal-Gen, a zero-dependency synthesis pipeline that autonomously generates executable and verifiable terminal training environments directly from domain specifications. Using this framework, we construct two large-scale resources: LiteCoder-Terminal-SFT, comprising 11,255 expert trajectories across 10 domains, and LiteCoder-Terminal-RL, featuring 602 verifiable environments for trajectory-level preference optimization. Supervised fine-tuning of Qwen-family models on our SFT dataset yields agents that significantly outperform their base counterparts. Notably, our 32B variant achieves 29.06%, 18.54%, and 34.00% pass@1 on Terminal Bench 1.0, 2.0, and Pro, respectively. Furthermore, applying Direct Multi-turn Preference Optimization (DMPO) on our RL environments yields additional performance gains. These results systematically demonstrate that fully synthetic, executable environments offer a scalable and verifiable supervision signal for mastering complex, real-world command-line workflows.

cs.CL↗

arXiv2025

Modeling and Optimization of Transistor Voltage Amplifiers Based on Stochastic Thermodynamics

As transistor sizes reach the mesoscopic scale, the limitations of traditional methods in ensuring thermodynamic consistency have made power dissipation optimization in transistor amplifiers a critical challenge. Based on stochastic thermodynamics, a transistor voltage amplifier model is first proposed as a new insight to investigate nonlinear relationships between the power dissipation and voltage gain for complementary symmetric voltage amplifier circuits (CSVACs). Utilizing the proposed model, the phenomenon, i.e., the power dissipation exponentially increases with the increase of voltage gain in CSVACs, is first clarified by an analytical expression to quantify the impact of voltage gain and input signal amplitude on the power dissipation. Considering the characteristic of power dissipation, a new multistage architecture is proposed to reduce the power dissipation in CSVACs. To optimize the power dissipation by adjusting the number of stages and the voltage gain at each stage, an optimal multistage scheme is proposed for multistage CSVACs. Simulation and experimental results show up to 99.36% and 94.59% power dissipation reduction compared with traditional CSVACs by the proposed optimal multistage scheme, respectively.

eess.SP↗

arXiv2023

Information Energy Ratio of XOR Logic Gate at Mesoscopic Scale

As the size of transistors approaches the mesoscopic scale, existing energy consumption analysis methods exhibit various limits, especially when being applied to describe the non-equilibrium information processing of transistors at ultra-low voltages. The stochastic thermodynamics offers a theoretic tool to analyze the energy consumption of transistor during the non-equilibrium information processing. Based on this theory, an information energy ratio of XOR gate composed of single-electron transistors is proposed at the mesoscopic scale, which can be used to quantify the exchange between the information and energy at XOR gates. Furthermore, the energy efficiency of the parity check circuit is proposed to analyze the energy consumption of digital signal processing systems. Compared with the energy efficiency of parity check circuit adopting the 7 nm semiconductor process supply voltage, simulation results show that the energy efficiency of the parity check circuit is improved by 266% when the supply voltage is chosen at a specified value.

cs.IT↗