paper-with-me

Papers

Deep Tabular Research via Continual Experience-Driven Execution

2026-03-10 · Junnan Dong, Chuang Zhou, Zheng Yuan, Yifei Yu, Qiufeng Wang, Yinghui Li, Siyu An, Di Yin, Xing Sun, Feiyue Huang arxiv

Large language models often struggle with complex long-horizon analytical tasks over unstructured tables, which typically feature hierarchical and bidirectional headers and non-canonical layouts. We formalize this challenge as Deep Tabular Research (DTR), requiring multi-step reasoning over interdependent table regions. To address DTR, we propose a novel agentic framework that treats tabular reasoning as a closed-loop decision-making process. We carefully design a coupled query and table comprehension for path decision making and operational execution. Specifically, (i) DTR first constructs a hierarchical meta graph to capture bidirectional semantics, mapping natural language queries into an operation-level search space; (ii) To navigate this space, we introduce an expectation-aware selection policy that prioritizes high-utility execution paths; (iii) Crucially, historical execution outcomes are synthesized into a siamese structured memory, i.e., parameterized updates and abstracted texts, enabling continual refinement. Extensive experiments on challenging unstructured tabular benchmarks verify the effectiveness and highlight the necessity of separating strategic planning from low-level execution for long-horizon tabular reasoning.

📄 PDF Abstract BibTeX arXiv:2603.09151

Code (0)

등록된 구현이 없습니다.

Tasks

Natural Language QueriesDecision Making

Similar Papers 제목 키워드 기반

Harness Continual Learning: Continual Adaptation Beyond Model Parameters

2026-08-19 · Borui Kang, Jinrui Gu, Junhan Lv, Wenbin Li 외 arxiv

Continual learning has largely been model-centric, treating model parameters as the state that changes with sequential experience. Modern agents can also adapt through a harness of prompts, memories, tools, skills, and r…

Continual Learning

CLeAN: Continual Learning Adaptive Normalization in Dynamic Environments

2026-03-18 · Isabella Marasco, Davide Evangelista, Elena Loli Piccolomini, Michele Colajanni arxiv

Artificial intelligence systems predominantly rely on static data distributions, making them ineffective in dynamic real-world environments, such as cybersecurity, autonomous transportation, or finance, where data shifts…

Continual Learning

Beyond Scaling: Self-Evolving LLM Agents for Hardware Kernel Optimization via an Experience-Driven Workflow and Experience Graph Memory

2026-08-26 · Siyuan Chen, Runlin Hou, Shenxiu Wu, Yansong Sun 외 arxiv

Hardware kernel optimization requires repeated compilation, correctness testing, profiling, and revision. LLM agents can automate parts of this process, and stronger foundation models, longer context windows, and longer …

Bridging Streaming Continual Learning via In-Context Large Tabular Models

2025-12-12 · Afonso Lourenço, João Gama, Eric P. Xing, Goreti Marreiros arxiv

In streaming scenarios, models must learn continuously, adapting to concept drifts without erasing previously acquired knowledge. However, existing research communities address these challenges in isolation. Continual Le…

Continual Learning

Design and Evaluation for Robust Continual Learning

2021-09-29 · Yeu-Shin Fu, Josh Milthorpe

Continual learning is the ability to learn from new experiences without forgetting previous experiences. Different continual learning methods are each motivated by their own interpretation of the continual learning scena…

Continual LearningExperimental Design