Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens

• URL: http://arxiv.org/abs/2601.09728v1
• Date: Sun, 28 Dec 2025 12:51:36 GMT
• Title: Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokens
• Authors: Meicong Zhang, Tiancheng su, Guoxiu He,
• Abstract summary: We propose eliminating external agentic to write research introductions.<n>Instead, we parameterize their logical structure into a large language model.<n>This allows the generation of a complete introduction in a single inference.
• Score: 3.6588919376939733
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: In recent years, using predefined agentic workflows to guide large language models (LLMs) for literature classification and review has become a research focus. However, writing research introductions is more challenging. It requires rigorous logic, coherent structure, and abstract summarization. Existing workflows often suffer from long reasoning chains, error accumulation, and reduced textual coherence. To address these limitations, we propose eliminating external agentic workflows. Instead, we directly parameterize their logical structure into the LLM. This allows the generation of a complete introduction in a single inference. To this end, we introduce the Stage Token for Introduction Generation (STIG). STIG converts the multiple stages of the original workflow into explicit stage signals. These signals guide the model to follow different logical roles and functions during generation. Through instruction tuning, the model learns the mapping between stage tokens and text functions. It also learns the logical order and transition patterns between stages, encoding this knowledge into the model parameters. Experimental results show that STIG can generate multi-stage text in a single inference. It does not require explicit workflow calls. STIG outperforms traditional agentic workflows and other baselines on metrics of semantic similarity and sentence-level structural rationality. The code is provided in the Supplementary Materials.

Related papers

• Step-Level Sparse Autoencoder for Reasoning Process Interpretation [48.99201531966593]
  Large Language Models (LLMs) have achieved strong complex reasoning capabilities through Chain-of-Thought (CoT) reasoning.<n>We propose step-level sparse autoencoder (SSAE), which serves as an analytical tool to disentangle different aspects of LLMs' reasoning steps into sparse features.<n> Experiments on multiple base models and reasoning tasks show the effectiveness of the extracted features.
  arXiv  Detail & Related papers  (2026-03-03T14:25:02Z)
• TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval [35.86480813138274]
  Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents.<n>We introduce TRACE (Task-adaptive Reasoning And Embeddings)<n>TRACE unifies generative reasoning with discriminative representation learning.
  arXiv  Detail & Related papers  (2026-03-03T12:36:39Z)
• RAVEL: Reasoning Agents for Validating and Evaluating LLM Text Synthesis [78.32151470154422]
  We introduce RAVEL, an agentic framework that enables the testers to autonomously plan and execute typical synthesis operations.<n>We present C3EBench, a benchmark comprising 1,258 samples derived from professional human writings.<n>By augmenting RAVEL with SOTA LLMs as operators, we find that such agentic text synthesis is dominated by the LLM's reasoning capability.
  arXiv  Detail & Related papers  (2026-02-28T14:47:34Z)
• Multi-Agent Procedural Graph Extraction with Structural and Logical Refinement [66.51979814832332]
  model formulates procedural graph extraction as a multi-round reasoning process with dedicated structural and logical refinement.<n>Experiments demonstrate that model achieves substantial improvements in both structural correctness and logical consistency over strong baselines.
  arXiv  Detail & Related papers  (2026-01-27T04:00:48Z)
• NUM2EVENT: Interpretable Event Reasoning from Numerical time-series [6.45945124018154]
  We introduce the task of number-to-event reasoning and decoding, which aims to infer interpretable structured events from numerical inputs.<n>To address the data scarcity and semantic alignment challenges, we propose a reasoning-aware framework.<n>Our model explicitly reasons over numerical changes, generates intermediate explanations, and outputs structured event hypotheses.
  arXiv  Detail & Related papers  (2025-10-24T02:57:11Z)
• Classifier-Augmented Generation for Structured Workflow Prediction [5.92079054629498]
  We propose a system that translates natural language descriptions into executables.<n>It automatically predicts both the structure and detailed configuration of the flow.<n>This is the first system with a detailed evaluation across stage prediction, edge layout, and property generation for natural-driven authoring.
  arXiv  Detail & Related papers  (2025-10-10T18:38:25Z)
• Contextualize-then-Aggregate: Circuits for In-Context Learning in Gemma-2 2B [51.74607395697567]
  In-Context Learning (ICL) is an intriguing ability of large language models (LLMs)<n>We use causal interventions to identify information flow in Gemma-2 2B for five naturalistic ICL tasks.<n>We find that the model infers task information using a two-step strategy we call contextualize-then-aggregate.
  arXiv  Detail & Related papers  (2025-03-31T18:33:55Z)
• Graph-DPEP: Decomposed Plug and Ensemble Play for Few-Shot Document Relation Extraction with Graph-of-Thoughts Reasoning [34.85741925091139]
  Graph-DPEP framework is grounded in the reasoning behind triplet explanation thoughts presented in natural language. We develop "ensemble-play", reapplying generation on the entire type list by leveraging the reasoning thoughts embedded in a sub-graph.
  arXiv  Detail & Related papers  (2024-11-05T07:12:36Z)
• Benchmarking Agentic Workflow Generation [80.74757493266057]
  We introduce WorfBench, a unified workflow generation benchmark with multi-faceted scenarios and intricate graph workflow structures.<n>We also present WorfEval, a systemic evaluation protocol utilizing subsequence and subgraph matching algorithms.<n>We observe that the generated can enhance downstream tasks, enabling them to achieve superior performance with less time during inference.
  arXiv  Detail & Related papers  (2024-10-10T12:41:19Z)
• Online Joint Fine-tuning of Multi-Agent Flows [12.851745991007169]
  I describe a procedure for online joint fine-tuning of an entire flow inspired by the Learning to Search framework. The approach leverages simulator access to reduce preferences over entire episodes to preferences over individual node outputs. I apply to the multi-hop QA dataset Musique achieving a state-of-the-art result.
  arXiv  Detail & Related papers  (2024-06-06T21:21:03Z)
• Instruction Position Matters in Sequence Generation with Large Language Models [67.87516654892343]
  Large language models (LLMs) are capable of performing conditional sequence generation tasks, such as translation or summarization. We propose enhancing the instruction-following capability of LLMs by shifting the position of task instructions after the input sentences.
  arXiv  Detail & Related papers  (2023-08-23T12:36:57Z)
• Guiding the PLMs with Semantic Anchors as Intermediate Supervision: Towards Interpretable Semantic Parsing [57.11806632758607]
  We propose to incorporate the current pretrained language models with a hierarchical decoder network. By taking the first-principle structures as the semantic anchors, we propose two novel intermediate supervision tasks. We conduct intensive experiments on several semantic parsing benchmarks and demonstrate that our approach can consistently outperform the baselines.
  arXiv  Detail & Related papers  (2022-10-04T07:27:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.