How to Train a Real-World Silicon Concierge? Internalizing Complex Business Workflow to Only OneModel (2026.acl-industry)
Copied to clipboard
| Challenge: | Traditional industrial agents rely on modular workflows that fracture into a labyrinth of ad-hoc patches, leading to cascading errors and high latency. |
| Approach: | They propose a paradigm shift from external workflows to internalized knowledge representation that consolidates complex business logic and SOPs directly into the model’s parameters. |
| Outcome: | The proposed model breaks the impossible triangle of latency, accuracy, and complexity. |
Similar Papers
Analyzing and Internalizing Complex Policy Documents for LLM Agents (2026.acl-long)
Copied to clipboard
Jiateng Liu, Zhenhailong Wang, Xiaojiang Huang, Yingjie Li, Xiang Li, Chenlei Guo, Xing Fan, Ruhi Sarikaya, Heng Ji
| Challenge: | Large language model agents rely on in-context policy documents to act as effective user assistants. |
| Approach: | They propose an agentic benchmark generator with Controllable Complexity in agent policy across four levels to evaluate agents under increasing complexity. |
| Outcome: | The proposed method outperforms the baseline in data-sparse and high-complexity settings. |
Internalizing Multi-Agent Reasoning for Accurate and Efficient LLM-based Recommendation (2026.findings-acl)
Copied to clipboard
| Challenge: | Large Language Models (LLMs) are reshaping recommender systems by leveraging extensive world knowledge and semantic reasoning to interpret user intent. |
| Approach: | They propose a single-agent Trajectory-Aligned Recommender to integrate reasoning capabilities into a model by a multi-agend teacher system. |
| Outcome: | The proposed model surpasses its teacher by 8.7% to 39.5% while eliminating iterative latency. |
LMFlow: An Extensible Toolkit for Finetuning and Inference of Large Foundation Models (2024.naacl-demo)
Copied to clipboard
| Challenge: | Foundation models have demonstrated a great ability to achieve general human-level intelligence far beyond traditional approaches. |
| Approach: | They propose a toolkit to simplify the finetuning of general foundation models. |
| Outcome: | The proposed toolkit simplifies the domain- and task-aware finetuning of general foundation models with limited computing resources. |
<SYNTACT>: Structuring Your Natural Language SOPs into Tailored Ambiguity-Resolved Code Templates (2025.emnlp-industry)
Copied to clipboard
Sachin Kumar Giroh, Pushpendu Ghosh, Aryan Jain, Harshal Giridhari Paunikar, Aditi Rastogi, Promod Yenigalla, Anish Nediyanchath
| Challenge: | Unstructured and ambiguous Standard Operating Procedures suffer from ambiguity, missing information, and inconsistency, all of which hinder automation. |
| Approach: | They propose a three-stage LLM framework that transforms unstructured SOPs into a structured plan and an executable code template. |
| Outcome: | The proposed framework shows an 88.4% accuracy and significant reduction in inconsistency on real-world SOPs and synthetic variants. |
LlamaDuo: LLMOps Pipeline for Seamless Migration from Service LLMs to Small-Scale Local LLMs (2025.acl-long)
Copied to clipboard
| Challenge: | LLMOps pipelines are used to migrate knowledge and abilities from service-oriented LLMs to smaller, locally manageable models. |
| Approach: | They propose an LLMOps pipeline for the seamless migration of knowledge and abilities from service-oriented LLMs to smaller, locally manageable models. |
| Outcome: | Experiments with leading-edge LLMs show that the proposed pipeline can scale to meet various tasks and domains. |
Synthesizing question answering data from financial documents: An End-to-End Multi-Agent Approach (2026.eacl-industry)
Copied to clipboard
| Challenge: | Large language models excel at financial reasoning but their deployment for enterprise use cases remains costly and often constrained by latency, privacy, and regulatory requirements. |
| Approach: | They propose a pipeline that extracts and selects relevant content from unstructured financial documents and generates QA pairs from the selected content for SLM fine-tuning. |
| Outcome: | The proposed model outperforms models trained on previous manual models and achieves competitive in-distribution performance. |
ComfyUI-R1: Exploring Reasoning Models for Workflow Generation (2026.findings-acl)
Copied to clipboard
| Challenge: | ComfyUI-R1 is the first large reasoning model for automated workflow generation. |
| Approach: | They propose a large reasoning model for automated workflow generation that builds on curated knowledge bases and a two-stage framework to fine-tune models for cold start and reinforcement learning for incentivizing reasoning capability. |
| Outcome: | The proposed model achieves 97% format validity rate, high pass rate, node-level and graph-level F1 scores, surpassing prior state-of-the-art methods that employ leading closed-source models such as GPT-4o and Claude series. |
OxyGent: Making Multi-Agent Systems Modular, Observable, and Evolvable via Oxy Abstraction (2026.acl-demo)
Copied to clipboard
| Challenge: | Existing MAS frameworks lack standardized abstractions, leading to low efficiency and repetitive implementation of core functions. |
| Approach: | They propose an open-source framework that encapsulates agents, tools, and reasoning flows as pluggable atomic components. |
| Outcome: | The OxyGent framework provides a robust and scalable foundation for multi-agent systems in industrial environments. |
Beyond Examples: Towards Automated Thought-level In-Context Reasoning for Large Language Models (2026.acl-long)
Copied to clipboard
Jinyang Wu, Mingkuan Feng, Shuai Zhang, Feihu Che, Zhengqi Wen, Chonghua Liao, Ling Yang, Haoran Luo, Zheng Lian, Jianhua Tao
| Challenge: | In-context learning (ICL) struggles with complex reasoning due to superficial, example-level implicit imitation. |
| Approach: | They propose an automated method that shifts from surface-level examples to more guidance-oriented thought patterns. |
| Outcome: | The proposed method achieves 80.6% accuracy on MATH and 62.5% on AMC, surpassing GPT-4o’s 77.2% and 57.5% accuracy. |
Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling (2026.findings-acl)
Copied to clipboard
Ivan Rodkin, Daniil Orel, Konstantin Smirnov, Arman Bolatov, Bilal Elbouardi, Besher Hassan, Yuri Kuratov, Aydar Bulatov, Preslav Nakov, Timothy Baldwin, Artem Shelmanov, Mikhail Burtsev
| Challenge: | Reasoning is a core capability of large language models, yet how multi-step reasoning is learned and executed remains unclear. |
| Approach: | They evaluate how large language models learn multi-step reasoning without memorization . they find that most neural architectures trained from scratch can learn rule inference . |
| Outcome: | The proposed framework fails to solve a natural-language proxy task with high accuracy. |