Searcharxiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.18507

The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization

Jiacheng Lin·Geoffrey Low·Nishit Agarwal·Rahul Jain·Afrah Shafquat·Mandis Beigi·Jimeng Sun
View original source ↗Read source document ↗Export metadata ↓

Abstract

Clinical trial protocols serve as the source of truth for study design, but are mostly written and used as unstructured PDF documents. Digitizing protocols turns static content into structured, machine-readable data that clinical software can analyze, validate, and execute. Coding agents, which select tools, execute code, and revise their approach as they work, are increasingly applied to such long-document tasks, yet it remains unclear how reliably they turn complete documents into accurate structured outputs. We study this question using protocol digitization as a testbed. We introduce TrialPD-Bench, an expert-annotated benchmark of 150 publicly available protocol PDFs spanning four task categories. Beyond final-answer performance, our evaluation measures evidence recall from agent traces, agent behavior, and cost. Across nine proprietary and open-weight models in five coding-agent harnesses, even the strongest agents do not fully solve protocol digitization. Our analysis further shows that agents usually locate the required evidence but fail in the last mile of transcribing and structuring it. We further develop TrialScribe, a domain-specific harness that equips coding agents with task skills and a verification loop. TrialScribe improves a locally served open-weight model by 6.2-59.4 points across eight metrics, enabling it to match or surpass proprietary models such as GPT-5.6-Sol.

Explore related subjects

cs.CL

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Jiacheng Lin, Geoffrey Low, Nishit Agarwal, Rahul Jain, Afrah Shafquat, Mandis Beigi, Jimeng Sun. 2026-10-13. The Last Mile of Coding Agents for Long-Document Tasks: An Empirical Study on Clinical Trial Protocol Digitization. https://arxiv.org/abs/2610.18507

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Beyond Size: How Gradients Shape Pruning Decisions in Large Language Models

Large Language Models (LLMs) with billions of parameters are prime targets for network pruning, which removes some model weights without hurting performance. Prior approaches such as magnitude pruning, SparseGPT, and Wanda either concentrated solely on weights or integrated weights with activations for sparsity. However, they overlooked the informative gradients derived from pretrained LLMs. In this paper, we present a novel sparsity-centric pruning method for pretrained LLMs, termed Gradient-based Language Model Pruner (GBLM-Pruner). GBLM-Pruner leverages the first-order term of the Taylor expansion, operating in a training-free manner by harnessing properly normalized gradients from a few calibration samples to determine the pruning metric, and substantially outperforms competitive counterparts like SparseGPT and Wanda in multiple benchmarks. Intriguingly, by incorporating gradients, unstructured pruning with our method tends to reveal some structural patterns, which mirrors the geometric interdependence inherent in the LLMs' parameter structure. Additionally, GBLM-Pruner functions without any subsequent retraining or weight updates to maintain its simplicity as other counterparts. Extensive evaluations on LLaMA-series, Qwen-Series and Deepseek models across zero-shot, STEM-Reasoning and Coding benchmarks show that GBLM-Pruner surpasses magnitude pruning and Wanda by significant margins and performs competitively against SparseGPT which involves intensive weight updates. We further extend our approach on Vision Transformer and Vision Language Models. Our code and models are available at https://github.com/VILA-Lab/GBLM-Pruner.

cs.CL↗
arXiv2026

$π$-CoT: Prolog-Initialized Chain-of-Thought Prompting for Multi-Hop Question-Answering

Chain-of-Thought (CoT) prompting significantly enhances large language models' (LLMs) problem-solving capabilities, but still struggles with complex multi-hop questions, often falling into circular reasoning patterns or deviating from the logical path entirely. This limitation is particularly acute in retrieval-augmented generation (RAG) settings, where obtaining the right context is critical. We introduce Prolog-Initialized Chain-of-Thought ($π$-CoT), a novel prompting strategy that combines logic programming's structural rigor with language models' flexibility. $π$-CoT reformulates multi-hop questions into Prolog queries decomposed as single-hop sub-queries. These are resolved sequentially, producing intermediate artifacts, with which we initialize the subsequent CoT reasoning procedure. Extensive experiments demonstrate that $π$-CoT matches or outperforms standard RAG and in-context CoT on multi-hop question-answering benchmarks, with the largest gains on questions for which retrieval surfaces the necessary evidence.

cs.CL↗
arXiv2026

Scaling Personality Control in LLMs with Big Five Scaler Prompts

We present Big5-Scaler, a prompt-based framework for conditioning large language models (LLMs) with controllable Big Five personality traits. By embedding numeric trait values into natural language prompts, our method enables fine-grained personality control without additional training. We evaluate Big5-Scaler across trait expression, dialogue generation, and human trait imitation tasks. Results show that it induces consistent and distinguishable personality traits across models, with performance varying by prompt type and scale. Our analysis highlights the effectiveness of concise prompts and lower trait intensities, providing a efficient approach for building personality-aware dialogue agents.

cs.CL↗