arXiv subjects

Daniel Xie

Publications and source records attributed to Daniel Xie.

5 recordsLinked to original sources

arXiv2026

A Multi-Agent Human-LLM Collaborative Framework for Closed-Loop Scientific Literature Summarization

Scientific discovery is slowed by fragmented literature that requires excessive human effort to gather, analyze, and understand. AI tools, including autonomous summarization and question answering, have been developed to aid in understanding scientific literature. However, these tools lack the structured, multi-step approach necessary for extracting deep insights from scientific literature. Large Language Models (LLMs) offer new possibilities for literature analysis, but remain unreliable due to hallucinations and incomplete extraction. We introduce Elhuyar, a multi-agent, human-in-the-loop system that integrates LLMs, structured AI, and human scientists to extract, analyze, and iteratively refine insights from scientific literature. The framework distributes tasks among specialized agents for filtering papers, extracting data, fitting models, and summarizing findings, with human oversight ensuring reliability. The system generates structured reports with extracted data, visualizations, model equations, and text summaries, enabling deeper inquiry through iterative refinement. Deployed in materials science, it analyzed literature on tungsten under helium-ion irradiation, showing experimentally correlated exponential helium bubble growth with irradiation dose and temperature, offering insight for plasma-facing materials (PFMs) in fusion reactors. This demonstrates how AI-assisted literature review can uncover scientific patterns and accelerate discovery.

cs.AI↗

arXiv2026

Reducing Hallucinations in LLM-based Scientific Literature Analysis Using Peer Context Outlier Detection

Reducing hallucinations in Large Language Models (LLMs) is essential for accurate data extraction from large text corpora. Current methods, like prompt engineering and chain-of-thought prompting, focus on individual documents and fail to consider relationships across a corpus. This paper introduces Peer Context Outlier Detection (P-COD), which uses inter-document relationships to improve extraction accuracy in scientific literature summarization, where papers with similar experiment settings should draw similar conclusions. By comparing extracted data to validated peer information within the corpus, we adjust confidence scores and flag low-confidence results for expert review. Our experiments demonstrate up to 98% precision in outlier detection across 6 scientific domains, reducing hallucinations and letting researchers focus on genuinely ambiguous cases.

cs.AI↗

arXiv2025

A broadband platform to search for hidden photons

The optical behavior of a structure consisting of graphene sheets embedded in media was studied, and the differences between the structure and ordinary birefringent crystal, double zero-reflectance point, were identified. We showed the changes in the optical behavior of the structure due to the existence of hidden photons. When a radiation illuminates the structure, only $\omega^2/\omega_p^2>1+\frac{m_X^2 c^4 \chi^2}{\epsilon_r\hbar^2\omega_p^2}$ can propagate through the structure. This provides a broadband platform for detecting hidden photons, where the sensitivity increases with the mass of the hidden photon.In contrast, if the mass of hidden photon is small, one can use a method similar to the light-shining-through-thin-wall technique. The structure is a platform to actively search for hidden photons since the operating point of the structure does not have to match the mass shell of hidden photons.

physics.optics↗

arXiv2025

Online Envy Minimization and Multicolor Discrepancy: Equivalences and Separations

We consider the fundamental problem of allocating $T$ indivisible items that arrive over time to $n$ agents with additive preferences, with the goal of minimizing envy. This problem is tightly connected to online multicolor discrepancy: vectors $v_1, \dots, v_T \in \mathbb{R}^d$ with $\| v_i \|_2 \leq 1$ arrive over time and must be, immediately and irrevocably, assigned to one of $n$ colors to minimize $\max_{i,j \in [n]} \| \sum_{v \in S_i} v - \sum_{v \in S_j} v \|_{\infty}$ at each step, where $S_\ell$ is the set of vectors that are assigned color $\ell$. The special case of $n = 2$ is called online vector balancing. Any bound for multicolor discrepancy implies the same bound for envy minimization. Against an adaptive adversary, both problems have the same optimal bound, $\Theta(\sqrt{T})$, but whether this holds for weaker adversaries is unknown. Against an oblivious adversary, Alweiss et al. give a $O(\log T)$ bound, with high probability, for multicolor discrepancy. Kulkarni et al. improve this to $O(\sqrt{\log T})$ for vector balancing and give a matching lower bound. Whether a $O(\sqrt{\log T})$ bound holds for multicolor discrepancy remains open. These results imply the best-known upper bounds for envy minimization (for an oblivious adversary) for $n$ and two agents, respectively; whether better bounds exist is open. In this paper, we resolve all aforementioned open problems. We prove that online envy minimization and multicolor discrepancy are equivalent against an oblivious adversary: we give a $O(\sqrt{\log T})$ upper bound for multicolor discrepancy, and a $\Omega(\sqrt{\log T})$ lower bound for envy minimization. For a weaker, i.i.d. adversary, we prove a separation: For online vector balancing, we give a $\Omega\left(\sqrt{\frac{\log T}{\log \log T}}\right)$ lower bound, while for envy minimization, we give an algorithm that guarantees a constant upper bound.

cs.GT↗

arXiv2022

Ion Sources for Production of Highly Charged Ion Beams

Intense Highly Charged Ion Beams (HCIB) from injector and charge-breeder ion sources at heavy ion accelerator facilities are in demand to expand research in particle and nuclear physics as well as for radiation effects testing. With current accelerator upgrades and advances in accelerator technologies, not all HCIB demands can be met with existing ion sources. Continued Research and Development (R&D) in this field are therefore essential to continually improve their performance and match the unprecedented and increasingly higher HCIB requirements from the accelerator community. This White Paper discusses the present production capabilities of ion sources of HCIB, and the potentials of future Highly Charged Ion (HCI) sources. It discusses the strengths and weaknesses of such sources along with paths forward for improving their performance to meet the requirements of present and future heavy ion accelerator facilities. This document is meant to be utilized as a basis to guide the conceptual design of future accelerators.

physics.acc-ph↗