RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation

• URL: http://arxiv.org/abs/2403.05313v1
• Date: Fri, 8 Mar 2024 13:42:19 GMT
• Title: RAT: Retrieval Augmented Thoughts Elicit Context-Aware Reasoning in Long-Horizon Generation
• Abstract summary: iterative revising a chain of thoughts significantly improves large language models' reasoning and generation ability. In particular, the proposed method revises each thought step one by one with retrieved information relevant to the task query. Applying RAT to GPT-3.5, GPT-4, and CodeLLaMA-7b substantially improves their performances on various long-horizon generation tasks.
• Score: 28.08775951425144
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We explore how iterative revising a chain of thoughts with the help of information retrieval significantly improves large language models' reasoning and generation ability in long-horizon generation tasks, while hugely mitigating hallucination. In particular, the proposed method -- *retrieval-augmented thoughts* (RAT) -- revises each thought step one by one with retrieved information relevant to the task query, the current and the past thought steps, after the initial zero-shot CoT is generated. Applying RAT to GPT-3.5, GPT-4, and CodeLLaMA-7b substantially improves their performances on various long-horizon generation tasks; on average of relatively increasing rating scores by 13.63% on code generation, 16.96% on mathematical reasoning, 19.2% on creative writing, and 42.78% on embodied task planning. The demo page can be found at https://craftjarvis.github.io/RAT

Related papers

• Recursive Experiential-Working Memory Evolution for Long-Horizon Agent Harnesses [83.32611586724165]
  Recuris is a Experiential-Working Memory architecture for long-horizon agent harnesses.<n>Working Memory tracks task progress and guides skill selection from Experiential Memory.<n>Across four long-horizon benchmarks and ten models, Recuris improves task success in 35 of the 37 completed model-benchmark pairs.
  arXiv  Detail & Related papers  (2026-08-25T17:56:35Z)
• How Well Can AI Generate Backlogs from App Mockups? [5.513644888428808]
  We propose a multimodal approach to support backlog generation from visual app mockups.<n>We study seven app development projects across two countries and interview developers about the results.
  arXiv  Detail & Related papers  (2026-07-24T20:40:22Z)
• Playful Agentic Robot Learning [108.08954330298549]
  We study Playful Agentic Robot Learning, where an embodied coding agent uses self-directed play as a continual skill-learning stage before downstream tasks arrive.<n>During play, RATs proposes novel yet learnable exploratory tasks, plans and executes robot-code policies, verifies intermediate progress, diagnoses failures, retries with dense, step-level feedback, and distills successful executions into a persistent code skill library.
  arXiv  Detail & Related papers  (2026-06-17T17:55:23Z)
• RAG over Thinking Traces Can Improve Reasoning Tasks [45.57562898423325]
  Retrieval-augmented generation (RAG) has proven effective for knowledge-intensive tasks, but is widely believed to offer limited benefit for reasoning-intensive problems.<n>We propose retrieving thinking traces, i.e., intermediate thinking trajectories generated during problem solving attempts.<n>Using these traces as a corpus, a simple retrieve-then-generate pipeline consistently improves reasoning performance.
  arXiv  Detail & Related papers  (2026-05-05T04:03:28Z)
• RoboMME: Benchmarking and Understanding Memory for Robotic Generalist Policies [54.23445842621374]
  Memory is critical for long-horizon and history-dependent robotic manipulation.<n>Recent vision-language-action (VLA) models have begun to incorporate memory mechanisms.<n>We introduce RoboMME: a large-scale standardized benchmark for evaluating and advancing VLA models.
  arXiv  Detail & Related papers  (2026-03-04T21:59:32Z)
• TeaRAG: A Token-Efficient Agentic Retrieval-Augmented Generation Framework [62.66056331998838]
  TeaRAG is a token-efficient agentic RAG framework capable of compressing both retrieval content and reasoning steps.<n>Our reward function evaluates the knowledge sufficiency by a knowledge matching mechanism, while penalizing excessive reasoning steps.
  arXiv  Detail & Related papers  (2025-11-07T16:08:34Z)
• Code Review Automation using Retrieval Augmented Generation [3.438467395627969]
  Code review is essential for maintaining software quality but is labor-intensive.<n> deep learning-based generative techniques and retrieval-based methods have demonstrated strong performance in this task.<n>We introduce Retrieval-Augmented Reviewer (RARe), which combines retrieval-based and generative methods.
  arXiv  Detail & Related papers  (2025-11-07T15:02:42Z)
• ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative Retrieval [125.19156877994612]
  Generative retrieval (GR) reformulates information retrieval (IR) by framing it as the generation of document identifiers (docids)<n>We propose textscZeroGR, a zero-shot generative retrieval framework that leverages natural language instructions to extend GR across a wide range of IR tasks.<n>Specifically, textscZeroGR is composed of three key components: (i) an LM-based docid generator that unifies heterogeneous documents into semantically meaningful docids; (ii) an instruction-tuned query generator that generates diverse types of queries from natural language task descriptions to enhance
  arXiv  Detail & Related papers  (2025-10-12T03:04:24Z)
• LongPerceptualThoughts: Distilling System-2 Reasoning for System-1 Perception [105.78609483419115]
  We introduce LongPerceptualThoughts, a new synthetic dataset with 30K long-thought traces for perceptual tasks. We propose a novel three-stage data synthesis framework that first synthesizes verifiable multiple-choice questions. We demonstrate notable improvements over existing visual reasoning data-generation methods.
  arXiv  Detail & Related papers  (2025-04-21T18:10:38Z)
• RAPID: Efficient Retrieval-Augmented Long Text Generation with Writing Planning and Information Discovery [69.41989381702858]
  Existing methods, such as direct generation and multi-agent discussion, often struggle with issues like hallucinations, topic incoherence, and significant latency. We propose RAPID, an efficient retrieval-augmented long text generation framework. Our work provides a robust and efficient solution to the challenges of automated long-text generation.
  arXiv  Detail & Related papers  (2025-03-02T06:11:29Z)
• Recursive Decomposition of Logical Thoughts: Framework for Superior Reasoning and Knowledge Propagation in Large Language Models [1.4956870931936515]
  We introduce RDoLT, a novel framework that significantly boosts Large Language Models reasoning performance. RDoLT is built on three key innovations: (1) breaking down complex reasoning tasks into sub-tasks of progressive complexity; (2) employing an advanced selection and scoring mechanism to identify the most promising reasoning thoughts; and (3) integrating a knowledge propagation module that mimics human learning. Our approach was evaluated across multiple benchmarks, including GSM8K, SVAMP, MultiArithm, LastLetterConcatenation, and Gaokao2023 Math.
  arXiv  Detail & Related papers  (2025-01-03T02:55:44Z)
• Prompting and Fine-tuning Large Language Models for Automated Code Review Comment Generation [5.6001617185032595]
  Large language models pretrained on both programming and natural language data tend to perform well in code-oriented tasks. We fine-tune open-source Large language models (LLM) in parameter-efficient, quantized low-rank fashion on consumer-grade hardware to improve review comment generation.
  arXiv  Detail & Related papers  (2024-11-15T12:01:38Z)
• P-RAG: Progressive Retrieval Augmented Generation For Planning on Embodied Everyday Task [94.08478298711789]
  Embodied Everyday Task is a popular task in the embodied AI community. Natural language instructions often lack explicit task planning. Extensive training is required to equip models with knowledge of the task environment.
  arXiv  Detail & Related papers  (2024-09-17T15:29:34Z)
• GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generation [103.3465421081531]
  VQAScore is a metric measuring the likelihood that a VQA model views an image as accurately depicting the prompt. Ranking by VQAScore is 2x to 3x more effective than other scoring methods like PickScore, HPSv2, and ImageReward. We release a new GenAI-Rank benchmark with over 40,000 human ratings to evaluate scoring metrics on ranking images generated from the same prompt.
  arXiv  Detail & Related papers  (2024-06-19T18:00:07Z)
• Language Modeling with Editable External Knowledge [90.7714362827356]
  This paper introduces ERASE, which improves model behavior when new documents are acquired. It incrementally deletes or rewriting other entries in the knowledge base each time a document is added. It improves accuracy relative to conventional retrieval-augmented generation by 7-13% (Mixtral-8x7B) and 6-10% (Llama-3-8B) absolute.
  arXiv  Detail & Related papers  (2024-06-17T17:59:35Z)
• The Chronicles of RAG: The Retriever, the Chunk and the Generator [0.0]
  This paper presents good practices to implement, optimize, and evaluate RAG for the Brazilian Portuguese language. We explore a diverse set of methods to answer questions about the first Harry Potter book.
  arXiv  Detail & Related papers  (2024-01-15T18:25:18Z)
• Alexpaca: Learning Factual Clarification Question Generation Without Examples [19.663171923249283]
  We present a new task that focuses on the ability to elicit missing information in multi-hop reasoning tasks. Humans outperform GPT-4 by a large margin, while Llama 3 8B Instruct does not even beat the dummy baseline in some metrics.
  arXiv  Detail & Related papers  (2023-10-17T20:40:59Z)
• A Critical Review of Large Language Model on Software Engineering: An Example from ChatGPT and Automated Program Repair [19.123640635549524]
  Large Language Models (LLMs) have been gaining increasing attention and demonstrated promising performance across a variety of software engineering tasks. This paper reviews the bug-fixing capabilities of ChatGPT on a clean APR benchmark with different research objectives. ChatGPT is able to fix 109 out of 151 buggy programs using the basic prompt within 35 independent rounds, outperforming state-of-the-art LLMs CodeT5 and PLBART by 27.5% and 62.4% prediction accuracy.
  arXiv  Detail & Related papers  (2023-10-13T06:11:47Z)
• Exploring the Potential of ChatGPT in Automated Code Refinement: An Empirical Study [0.0]
  ChatGPT, a cutting-edge language model, has demonstrated impressive performance in various natural language processing tasks. We conduct the first empirical study to understand the capabilities of ChatGPT in code review tasks. Our results show that ChatGPT achieves higher EM and BLEU scores of 22.78 and 76.44 respectively, while the state-of-the-art method achieves only 15.50 and 62.88 on a high-quality code review dataset.
  arXiv  Detail & Related papers  (2023-09-15T07:41:33Z)
• Learning to Rank in Generative Retrieval [62.91492903161522]
  Generative retrieval aims to generate identifier strings of relevant passages as the retrieval target. We propose a learning-to-rank framework for generative retrieval, dubbed LTRGR. This framework only requires an additional learning-to-rank training phase to enhance current generative retrieval systems.
  arXiv  Detail & Related papers  (2023-06-27T05:48:14Z)
• Grounded Keys-to-Text Generation: Towards Factual Open-Ended Generation [92.1582872870226]
  We propose a new grounded keys-to-text generation task. The task is to generate a factual description about an entity given a set of guiding keys, and grounding passages. Inspired by recent QA-based evaluation measures, we propose an automatic metric, MAFE, for factual correctness of generated descriptions.
  arXiv  Detail & Related papers  (2022-12-04T23:59:41Z)
• Generative Conversational Networks [67.13144697969501]
  We propose a framework called Generative Conversational Networks, in which conversational agents learn to generate their own labelled training data. We show an average improvement of 35% in intent detection and 21% in slot tagging over a baseline model trained from the seed data.
  arXiv  Detail & Related papers  (2021-06-15T23:19:37Z)

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.