Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models

• URL: http://arxiv.org/abs/2408.06458v2
• Date: Mon, 4 Nov 2024 21:04:31 GMT
• Title: Towards Autonomous Agents: Adaptive-planning, Reasoning, and Acting in Language Models
• Authors: Abhishek Dutta, Yen-Che Hsiao,
• Abstract summary: We propose a novel in-context learning algorithm for building autonomous decision-making language agents. Our selected language agent demonstrates the ability to solve tasks in a text-based game environment.
• Score: 3.8936716676293917
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: We propose a novel in-context learning algorithm for building autonomous decision-making language agents. The language agent continuously attempts to solve the same task by self-correcting each time the task fails. Our selected language agent demonstrates the ability to solve tasks in a text-based game environment. Our results show that the gemma-2-9b-it language model, using our proposed method, can successfully complete two of six tasks that failed in the first attempt. This highlights the effectiveness of our approach in enhancing the problem-solving capabilities of a single language model through self-correction, paving the way for more advanced autonomous agents. The code is publicly available at https://github.com/YenCheHsiao/AutonomousLLMAgentwithAdaptingPlanning.

Related papers

• AdaMergeX: Cross-Lingual Transfer with Large Language Models via Adaptive Adapter Merging [96.39773974044041]
  Cross-lingual transfer is an effective alternative to the direct fine-tuning on target tasks in specific languages. We propose a new cross-lingual transfer method called $textttAdaMergeX$ that utilizes adaptive adapter merging. Our empirical results demonstrate that our approach yields new and effective cross-lingual transfer, outperforming existing methods across all settings.
  arXiv  Detail & Related papers  (2024-02-29T07:11:24Z)
• Self Generated Wargame AI: Double Layer Agent Task Planning Based on Large Language Model [0.6562256987706128]
  This paper innovatively applies the large language model to the field of intelligent decision-making. It proposes a two-layer agent task planning, issues and executes decision commands through the interaction of natural language. It is found that the intelligent decision-making ability of the large language model is significantly stronger than the commonly used reinforcement learning AI and rule AI.
  arXiv  Detail & Related papers  (2023-12-02T09:45:45Z)
• UniverSLU: Universal Spoken Language Understanding for Diverse Tasks with Natural Language Instructions [64.50935101415776]
  We build a single model that jointly performs various spoken language understanding (SLU) tasks. We demonstrate the efficacy of our single multi-task learning model "UniverSLU" for 12 speech classification and sequence generation task types spanning 17 datasets and 9 languages.
  arXiv  Detail & Related papers  (2023-10-04T17:10:23Z)
• Why Does Zero-Shot Cross-Lingual Generation Fail? An Explanation and a Solution [0.9085116579988537]
  We show that the fine-tuning process learns language invariant representations, which is beneficial for classification tasks but harmful for generation tasks. Experiments on three semantically diverse generation tasks show that our method reduces the accidental translation problem by 68% and improves the ROUGE-L score by 1.5 on average.
  arXiv  Detail & Related papers  (2023-05-27T02:04:19Z)
• Grounding Language with Visual Affordances over Unstructured Data [26.92329260907805]
  We propose a novel approach to efficiently learn language-conditioned robot skills from unstructured, offline and reset-free data. We exploit a self-supervised visuo-lingual affordance model, which requires as little as 1% of the total data with language. We find that our method is capable of completing long-horizon, multi-tier tasks in the real world, while requiring an order of magnitude less data than previous approaches.
  arXiv  Detail & Related papers  (2022-10-04T21:16:48Z)
• Bridging the Gap Between Training and Inference of Bayesian Controllable Language Models [58.990214815032495]
  Large-scale pre-trained language models have achieved great success on natural language generation tasks. BCLMs have been shown to be efficient in controllable language generation. We propose a "Gemini Discriminator" for controllable language generation which alleviates the mismatch problem with a small computational cost.
  arXiv  Detail & Related papers  (2022-06-11T12:52:32Z)
• Context-Aware Language Modeling for Goal-Oriented Dialogue Systems [84.65707332816353]
  We formulate goal-oriented dialogue as a partially observed Markov decision process. We derive a simple and effective method to finetune language models in a goal-aware way. We evaluate our method on a practical flight-booking task using AirDialogue.
  arXiv  Detail & Related papers  (2022-04-18T17:23:11Z)
• Quality Assurance of Generative Dialog Models in an Evolving Conversational Agent Used for Swedish Language Practice [59.705062519344]
  One proposed solution involves AI-enabled conversational agents for person-centered interactive language practice. We present results from ongoing action research targeting quality assurance of proprietary generative dialog models trained for virtual job interviews.
  arXiv  Detail & Related papers  (2022-03-29T10:25:13Z)
• Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognition [80.446770909975]
  Linguistic knowledge is of great benefit to scene text recognition. How to effectively model linguistic rules in end-to-end deep networks remains a research challenge. We propose an autonomous, bidirectional and iterative ABINet for scene text recognition.
  arXiv  Detail & Related papers  (2021-03-11T06:47:45Z)

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.