Resource Constraints and Performance in Agentic AI Systems
研究通过对比OpenClaw和NanoBot两种自主AI系统在任务完成率、资源消耗等方面的表现，探讨了如何评估更加自主的AI系统的进展。
0 citationsRead paper
Selected work
Representative Papers
Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization
This work addresses the challenge of inaccurate geometry recovery in 3D Gaussian Splatting under limited viewing conditions, where irregular Gaussian primitives hinder effective geometric refinement. To overcome this, the authors propose an end-to-end differentiable framework that anchors Gaussian primitives to a differentiable signed distance field (SDF). The approach employs a bilevel optimization strategy: the outer loop updates the underlying geometry via the SDF, while the inner loop refines Gaussian attributes. Additionally, a Gaussian-surface consistency constraint and an octree-based multi-resolution subdivision mechanism are introduced to suppress redundant surfaces and complete missing structures. This method achieves high-quality joint reconstruction of geometry and appearance even from low-resolution inputs.
0 citationsRead paper
Georeferencing Non-Gazetteered Place Names using Biological Specimen Records
This study addresses the challenge of geolocating non-standard geographic place names (NGPs) in historical biological specimen records that are absent from modern gazetteers. The authors propose a novel text-based spatial reasoning framework that systematically integrates recurrent NGPs and their associated spatial relationship descriptions from specimen metadata. They evaluate three distinct approaches—deterministic modeling, probabilistic inference, and large language models (LLMs)—on a benchmark dataset of pseudo-NGPs. Experimental results demonstrate that probabilistic inference achieves the highest accuracy, yielding a median localization error of 1.43 kilometers and a 36% success rate within 1 kilometer, outperforming LLMs, which attain a median error of 1.80 kilometers and 31% 1-kilometer accuracy. This work establishes an effective new paradigm for precise georeferencing of historical biogeographic data.
0 citationsRead paper
Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis Using an Agentic Harness
This study addresses the lack of executable and verifiable knowledge representations in existing meta-analyses, which hinders the traceability and reproducibility of critical analytical decisions. To overcome this limitation, the authors propose Executable Analytical Knowledge Representation (EAKR) and introduce MetaSynDec, an agent-based framework that, for the first time, enables explicit modeling, machine-actionable execution, and closed-loop validation of meta-analytic decisions. The system leverages large language models to generate structured knowledge and validates and executes it through deterministic, schema- and contract-based services. Evaluated across 58 synthesis units, EAKR successfully constructed all units, achieved exact evidence-set consistency in 75% of cases, and produced confidence intervals overlapping with published results in 98.2% of cases—substantially outperforming direct LLM-generated approaches.
0 citationsRead paper
Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning
This study investigates whether existing LoRA variants offer advantages over standard LoRA in balancing cross-lingual transfer and knowledge retention during multilingual instruction tuning. We systematically evaluate the base LoRA and four of its variants on two multilingual datasets, complemented by an analysis of hidden embeddings to compare internal language representations. Our empirical results—presented for the first time—demonstrate that more complex architectural modifications to LoRA do not yield significant improvements in cross-lingual adaptability. The variants perform comparably to standard LoRA in both cross-lingual transfer and knowledge retention, and fine-tuned models exhibit highly similar inter-layer language representations across all variants. These findings challenge the prevailing assumption that enhanced LoRA architectures inherently confer superior multilingual capabilities.
0 citationsRead paper
Recent publications
Latest Papers
Resource Constraints and Performance in Agentic AI Systems
研究通过对比OpenClaw和NanoBot两种自主AI系统在任务完成率、资源消耗等方面的表现，探讨了如何评估更加自主的AI系统的进展。
0 citationsRead paper
Gaussian Sculpting: End-to-End Controllable Surface Reconstruction via Field Optimization
This work addresses the challenge of inaccurate geometry recovery in 3D Gaussian Splatting under limited viewing conditions, where irregular Gaussian primitives hinder effective geometric refinement. To overcome this, the authors propose an end-to-end differentiable framework that anchors Gaussian primitives to a differentiable signed distance field (SDF). The approach employs a bilevel optimization strategy: the outer loop updates the underlying geometry via the SDF, while the inner loop refines Gaussian attributes. Additionally, a Gaussian-surface consistency constraint and an octree-based multi-resolution subdivision mechanism are introduced to suppress redundant surfaces and complete missing structures. This method achieves high-quality joint reconstruction of geometry and appearance even from low-resolution inputs.
0 citationsRead paper
Georeferencing Non-Gazetteered Place Names using Biological Specimen Records
This study addresses the challenge of geolocating non-standard geographic place names (NGPs) in historical biological specimen records that are absent from modern gazetteers. The authors propose a novel text-based spatial reasoning framework that systematically integrates recurrent NGPs and their associated spatial relationship descriptions from specimen metadata. They evaluate three distinct approaches—deterministic modeling, probabilistic inference, and large language models (LLMs)—on a benchmark dataset of pseudo-NGPs. Experimental results demonstrate that probabilistic inference achieves the highest accuracy, yielding a median localization error of 1.43 kilometers and a 36% success rate within 1 kilometer, outperforming LLMs, which attain a median error of 1.80 kilometers and 31% 1-kilometer accuracy. This work establishes an effective new paradigm for precise georeferencing of historical biogeographic data.
0 citationsRead paper
Constructing Executable Analytical Knowledge Representations for Meta-Analysis Synthesis Using an Agentic Harness
This study addresses the lack of executable and verifiable knowledge representations in existing meta-analyses, which hinders the traceability and reproducibility of critical analytical decisions. To overcome this limitation, the authors propose Executable Analytical Knowledge Representation (EAKR) and introduce MetaSynDec, an agent-based framework that, for the first time, enables explicit modeling, machine-actionable execution, and closed-loop validation of meta-analytic decisions. The system leverages large language models to generate structured knowledge and validates and executes it through deterministic, schema- and contract-based services. Evaluated across 58 synthesis units, EAKR successfully constructed all units, achieved exact evidence-set consistency in 75% of cases, and produced confidence intervals overlapping with published results in 98.2% of cases—substantially outperforming direct LLM-generated approaches.
0 citationsRead paper
Which LoRA? An Empirical Study on the Effectiveness of LoRA Techniques During Multilingual Instruction Tuning
This study investigates whether existing LoRA variants offer advantages over standard LoRA in balancing cross-lingual transfer and knowledge retention during multilingual instruction tuning. We systematically evaluate the base LoRA and four of its variants on two multilingual datasets, complemented by an analysis of hidden embeddings to compare internal language representations. Our empirical results—presented for the first time—demonstrate that more complex architectural modifications to LoRA do not yield significant improvements in cross-lingual adaptability. The variants perform comparably to standard LoRA in both cross-lingual transfer and knowledge retention, and fine-tuned models exhibit highly similar inter-layer language representations across all variants. These findings challenge the prevailing assumption that enhanced LoRA architectures inherently confer superior multilingual capabilities.
0 citationsRead paper