Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery

• URL: http://arxiv.org/abs/2404.00756v1
• Date: Sun, 31 Mar 2024 17:54:22 GMT
• Title: Recover: A Neuro-Symbolic Framework for Failure Detection and Recovery
• Authors: Cristina Cornelio, Mohammed Diab,
• Abstract summary: This paper introduces Recover, a neuro-symbolic framework for online failure identification and recovery. By integrating logical rules, and LLM-based planners, Recover exploits symbolic information to enhance the ability of LLMs to generate recovery plans.
• Score: 2.0554045007430672
• License: http://creativecommons.org/publicdomain/zero/1.0/
• Abstract: Recognizing failures during task execution and implementing recovery procedures is challenging in robotics. Traditional approaches rely on the availability of extensive data or a tight set of constraints, while more recent approaches leverage large language models (LLMs) to verify task steps and replan accordingly. However, these methods often operate offline, necessitating scene resets and incurring in high costs. This paper introduces Recover, a neuro-symbolic framework for online failure identification and recovery. By integrating ontologies, logical rules, and LLM-based planners, Recover exploits symbolic information to enhance the ability of LLMs to generate recovery plans and also to decrease the associated costs. In order to demonstrate the capabilities of our method in a simulated kitchen environment, we introduce OntoThor, an ontology describing the AI2Thor simulator setting. Empirical evaluation shows that OntoThor's logical rules accurately detect all failures in the analyzed tasks, and that Recover considerably outperforms, for both failure detection and recovery, a baseline method reliant solely on LLMs.

Related papers

• RecoveryChaining: Learning Local Recovery Policies for Robust Manipulation [41.38308130776887]
  We propose to use hierarchical reinforcement learning to learn a separate recovery policy for a robot. The recovery policy is triggered when a failure is detected based on sensory observations and seeks to take the robot to a state from which it can complete the task. We evaluate our approach in three multi-step manipulation tasks with sparse rewards, where it learns significantly more robust recovery policies than those learned by baselines.
  arXiv  Detail & Related papers  (2024-10-17T19:14:43Z)
• Directed Exploration in Reinforcement Learning from Linear Temporal Logic [59.707408697394534]
  Linear temporal logic (LTL) is a powerful language for task specification in reinforcement learning. We show that the synthesized reward signal remains fundamentally sparse, making exploration challenging. We show how better exploration can be achieved by further leveraging the specification and casting its corresponding Limit Deterministic B"uchi Automaton (LDBA) as a Markov reward process.
  arXiv  Detail & Related papers  (2024-08-18T14:25:44Z)
• Cognitive LLMs: Towards Integrating Cognitive Architectures and Large Language Models for Manufacturing Decision-making [51.737762570776006]
  LLM-ACTR is a novel neuro-symbolic architecture that provides human-aligned and versatile decision-making. Our framework extracts and embeds knowledge of ACT-R's internal decision-making process as latent neural representations. Our experiments on novel Design for Manufacturing tasks show both improved task performance as well as improved grounded decision-making capability.
  arXiv  Detail & Related papers  (2024-08-17T11:49:53Z)
• RAGEval: Scenario Specific RAG Evaluation Dataset Generation Framework [69.4501863547618]
  This paper introduces RAGEval, a framework designed to assess RAG systems across diverse scenarios. With a focus on factual accuracy, we propose three novel metrics Completeness, Hallucination, and Irrelevance. Experimental results show that RAGEval outperforms zero-shot and one-shot methods in terms of clarity, safety, conformity, and richness of generated samples.
  arXiv  Detail & Related papers  (2024-08-02T13:35:11Z)
• MR-Ben: A Meta-Reasoning Benchmark for Evaluating System-2 Thinking in LLMs [55.20845457594977]
  Large language models (LLMs) have shown increasing capability in problem-solving and decision-making. We present a process-based benchmark MR-Ben that demands a meta-reasoning skill. Our meta-reasoning paradigm is especially suited for system-2 slow thinking.
  arXiv  Detail & Related papers  (2024-06-20T03:50:23Z)
• Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More? [54.667202878390526]
  Long-context language models (LCLMs) have the potential to revolutionize our approach to tasks traditionally reliant on external tools like retrieval systems or databases. We introduce LOFT, a benchmark of real-world tasks requiring context up to millions of tokens designed to evaluate LCLMs' performance on in-context retrieval and reasoning. Our findings reveal LCLMs' surprising ability to rival state-of-the-art retrieval and RAG systems, despite never having been explicitly trained for these tasks.
  arXiv  Detail & Related papers  (2024-06-19T00:28:58Z)
• DORY: Deliberative Prompt Recovery for LLM [11.988508965818767]
  Deliberative PrOmpt RecoverY (DORY) is a novel approach that leverages uncertainty to recover prompts accurately. DORY involves reconstructing drafts from outputs, refining these with hints, and filtering out noise based on uncertainty. Our evaluation shows that DORY outperforms existing baselines, improving performance by approximately 10.82%.
  arXiv  Detail & Related papers  (2024-05-31T07:51:16Z)
• Neural Fault Injection: Generating Software Faults from Natural Language [6.050976240234865]
  This paper introduces a novel methodology that harnesses the capabilities of Large Language Models (LLMs) augmented with Reinforcement Learning from Human Feedback (RLHF) The usage of RLHF emphasizes an iterative refinement process, allowing testers to provide feedback on generated faults. This innovative methodology aims to significantly reduce the manual effort involved in crafting fault scenarios as it allows testers to focus on higher-level testing strategies.
  arXiv  Detail & Related papers  (2024-04-11T05:59:16Z)
• Characterization of Large Language Model Development in the Datacenter [55.9909258342639]
  Large Language Models (LLMs) have presented impressive performance across several transformative tasks. However, it is non-trivial to efficiently utilize large-scale cluster resources to develop LLMs. We present an in-depth characterization study of a six-month LLM development workload trace collected from our GPU datacenter Acme.
  arXiv  Detail & Related papers  (2024-03-12T13:31:14Z)
• Proactive and AoI-aware Failure Recovery for Stateful NFV-enabled Zero-Touch 6G Networks: Model-Free DRL Approach [0.0]
  We propose a model-free deep reinforcement learning (DRL)-based proactive failure recovery framework called zero-touch PFR (ZT-PFR) ZT-PFR is for the embedded stateful virtual network functions (VNFs) in network function virtualization (NFV) enabled networks.
  arXiv  Detail & Related papers  (2021-02-02T21:40:35Z)
• Recovery command generation towards automatic recovery in ICT systems by Seq2Seq learning [11.387419806996599]
  We propose a method of estimating recovery commands by using Seq2Seq, a neural network model. When a new failure occurs, our method estimates plausible commands that recover from the failure on the basis of collected logs.
  arXiv  Detail & Related papers  (2020-03-24T11:34:10Z)

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.