Self-Taught Agentic Long Context Understanding
- URL: http://arxiv.org/abs/2502.15920v1
- Date: Fri, 21 Feb 2025 20:29:36 GMT
- Title: Self-Taught Agentic Long Context Understanding
- Authors: Yufan Zhuang, Xiaodong Yu, Jialian Wu, Ximeng Sun, Ze Wang, Jiang Liu, Yusheng Su, Jingbo Shang, Zicheng Liu, Emad Barsoum,
- Abstract summary: AgenticLU is a framework designed to integrate targeted self-clarification with contextual grounding.<n>AgenticLU achieves 97.8% answer recall on NarrativeQA with a search depth of up to three and a branching factor of eight.
- Score: 47.186303525057475
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Answering complex, long-context questions remains a major challenge for large language models (LLMs) as it requires effective question clarifications and context retrieval. We propose Agentic Long-Context Understanding (AgenticLU), a framework designed to enhance an LLM's understanding of such queries by integrating targeted self-clarification with contextual grounding within an agentic workflow. At the core of AgenticLU is Chain-of-Clarifications (CoC), where models refine their understanding through self-generated clarification questions and corresponding contextual groundings. By scaling inference as a tree search where each node represents a CoC step, we achieve 97.8% answer recall on NarrativeQA with a search depth of up to three and a branching factor of eight. To amortize the high cost of this search process to training, we leverage the preference pairs for each step obtained by the CoC workflow and perform two-stage model finetuning: (1) supervised finetuning to learn effective decomposition strategies, and (2) direct preference optimization to enhance reasoning quality. This enables AgenticLU models to generate clarifications and retrieve relevant context effectively and efficiently in a single inference pass. Extensive experiments across seven long-context tasks demonstrate that AgenticLU significantly outperforms state-of-the-art prompting methods and specialized long-context LLMs, achieving robust multi-hop reasoning while sustaining consistent performance as context length grows.
Related papers
- A Survey of Frontiers in LLM Reasoning: Inference Scaling, Learning to Reason, and Agentic Systems [93.8285345915925]
Reasoning is a fundamental cognitive process that enables logical inference, problem-solving, and decision-making.
With the rapid advancement of large language models (LLMs), reasoning has emerged as a key capability that distinguishes advanced AI systems.
We categorize existing methods along two dimensions: (1) Regimes, which define the stage at which reasoning is achieved; and (2) Architectures, which determine the components involved in the reasoning process.
arXiv Detail & Related papers (2025-04-12T01:27:49Z) - FactGuard: Leveraging Multi-Agent Systems to Generate Answerable and Unanswerable Questions for Enhanced Long-Context LLM Extraction [25.00896070082754]
Extractive reading comprehension systems are designed to locate the correct answer to a question within a given text.
A persistent challenge lies in ensuring these models maintain high accuracy in answering questions while reliably recognizing unanswerable queries.
We propose an innovative data augmentation methodology grounded in a multi-agent collaborative framework.
arXiv Detail & Related papers (2025-04-08T01:45:16Z) - Towards more Contextual Agents: An extractor-Generator Optimization Framework [0.0]
Large Language Model (LLM)-based agents have demonstrated remarkable success in solving complex tasks across a wide range of general-purpose applications.<n>However, their performance often degrades in context-specific scenarios, such as specialized industries or research domains.<n>To address this challenge, our work introduces a systematic approach to enhance the contextual adaptability of LLM-based agents.
arXiv Detail & Related papers (2025-02-18T15:07:06Z) - QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search [89.97082652805904]
We propose QLASS (Q-guided Language Agent Stepwise Search), to automatically generate annotations by estimating Q-values.<n>With the stepwise guidance, we propose a Q-guided generation strategy to enable language agents to better adapt to long-term value.<n>We empirically demonstrate that QLASS can lead to more effective decision making through qualitative analysis.
arXiv Detail & Related papers (2025-02-04T18:58:31Z) - Insight-V: Exploring Long-Chain Visual Reasoning with Multimodal Large Language Models [64.1799100754406]
Large Language Models (LLMs) demonstrate enhanced capabilities and reliability by reasoning more.
Despite various efforts to improve LLM reasoning, high-quality long-chain reasoning data and optimized training pipelines still remain inadequately explored in vision-language tasks.
We present Insight-V, an early effort to 1) scalably produce long and robust reasoning data for complex multi-modal tasks, and 2) an effective training pipeline to enhance the reasoning capabilities of MLLMs.
arXiv Detail & Related papers (2024-11-21T18:59:55Z) - Textualized Agent-Style Reasoning for Complex Tasks by Multiple Round LLM Generation [49.27250832754313]
We present AgentCOT, a llm-based autonomous agent framework.
At each step, AgentCOT selects an action and executes it to yield an intermediate result with supporting evidence.
We introduce two new strategies to enhance the performance of AgentCOT.
arXiv Detail & Related papers (2024-09-19T02:20:06Z) - Strategic Chain-of-Thought: Guiding Accurate Reasoning in LLMs through Strategy Elicitation [16.350747493026432]
The Chain-of-Thought (CoT) paradigm has emerged as a critical approach for enhancing the reasoning capabilities of large language models (LLMs)
We propose the textbfStrategic Chain-of-Thought (SCoT) to refine LLM performance by integrating strategic knowledge prior to generating intermediate reasoning steps.
SCoT employs a two-stage approach within a single prompt: first eliciting an effective problem-solving strategy, which is then used to guide the generation of high-quality CoT paths and final answers.
arXiv Detail & Related papers (2024-09-05T06:28:05Z) - Chain of Agents: Large Language Models Collaborating on Long-Context Tasks [39.27648679819897]
Chain-of-Agents (CoA) is a novel framework that harnesses multi-agent collaboration through natural language to enable information aggregation and context reasoning.
CoA processes the entire input by interleaving reading and reasoning, and it mitigates long context focus issues by assigning each agent a short context.
arXiv Detail & Related papers (2024-06-04T23:36:08Z) - Self-Convinced Prompting: Few-Shot Question Answering with Repeated
Introspection [13.608076739368949]
We introduce a novel framework that harnesses the potential of large-scale pre-trained language models.
Our framework processes the output of a typical few-shot chain-of-thought prompt, assesses the correctness of the response, scrutinizes the answer, and ultimately produces a new solution.
arXiv Detail & Related papers (2023-10-08T06:36:26Z) - DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for
In-Context Learning [66.85379279041128]
In this study, we introduce a framework that leverages Dual Queries and Low-rank approximation Re-ranking to automatically select exemplars for in-context learning.
DQ-LoRe significantly outperforms prior state-of-the-art methods in the automatic selection of exemplars for GPT-4, enhancing performance from 92.5% to 94.2%.
arXiv Detail & Related papers (2023-10-04T16:44:37Z) - Improving Open Information Extraction with Large Language Models: A
Study on Demonstration Uncertainty [52.72790059506241]
Open Information Extraction (OIE) task aims at extracting structured facts from unstructured text.
Despite the potential of large language models (LLMs) like ChatGPT as a general task solver, they lag behind state-of-the-art (supervised) methods in OIE tasks.
arXiv Detail & Related papers (2023-09-07T01:35:24Z)
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.