Mars: Situated Inductive Reasoning in an Open-World Environment
- URL: http://arxiv.org/abs/2410.08126v2
- Date: Thu, 31 Oct 2024 11:11:18 GMT
- Title: Mars: Situated Inductive Reasoning in an Open-World Environment
- Authors: Xiaojuan Tang, Jiaqi Li, Yitao Liang, Song-chun Zhu, Muhan Zhang, Zilong Zheng,
- Abstract summary: In this paper, we design Mars, an interactive environment devised for situated inductive reasoning.
It introduces counter-commonsense game mechanisms by modifying terrain, survival setting and task dependency.
In Mars, agents need to actively interact with their surroundings, derive useful rules and perform decision-making tasks in specific contexts.
- Score: 77.14465960780726
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Large Language Models (LLMs) trained on massive corpora have shown remarkable success in knowledge-intensive tasks. Yet, most of them rely on pre-stored knowledge. Inducing new general knowledge from a specific environment and performing reasoning with the acquired knowledge -- \textit{situated inductive reasoning}, is crucial and challenging for machine intelligence. In this paper, we design Mars, an interactive environment devised for situated inductive reasoning. It introduces counter-commonsense game mechanisms by modifying terrain, survival setting and task dependency while adhering to certain principles. In Mars, agents need to actively interact with their surroundings, derive useful rules and perform decision-making tasks in specific contexts. We conduct experiments on various RL-based and LLM-based methods, finding that they all struggle on this challenging situated inductive reasoning benchmark. Furthermore, we explore \textit{Induction from Reflection}, where we instruct agents to perform inductive reasoning from history trajectory. The superior performance underscores the importance of inductive reasoning in Mars. Through Mars, we aim to galvanize advancements in situated inductive reasoning and set the stage for developing the next generation of AI systems that can reason in an adaptive and context-sensitive way.
Related papers
- Enabling High-Level Machine Reasoning with Cognitive Neuro-Symbolic
Systems [67.01132165581667]
We propose to enable high-level reasoning in AI systems by integrating cognitive architectures with external neuro-symbolic components.
We illustrate a hybrid framework centered on ACT-R and we discuss the role of generative models in recent and future applications.
arXiv Detail & Related papers (2023-11-13T21:20:17Z) - Active Reasoning in an Open-World Environment [29.596555383319814]
$Conan$ is an interactive open-world environment devised for the assessment of active reasoning.
$Conan$ facilitates active exploration and promotes multi-round abductive inference, reminiscent of rich, open-world settings like Minecraft.
Our analysis underscores the shortcomings of contemporary state-of-the-art models in active exploration and understanding complex scenarios.
arXiv Detail & Related papers (2023-11-03T16:24:34Z) - tagE: Enabling an Embodied Agent to Understand Human Instructions [3.943519623674811]
We introduce a novel system known as task and argument grounding for Embodied agents (tagE)
At its core, our system employs an inventive neural network model designed to extract a series of tasks from complex task instructions expressed in natural language.
Our proposed model adopts an encoder-decoder framework enriched with nested decoding to effectively extract tasks and their corresponding arguments from these intricate instructions.
arXiv Detail & Related papers (2023-10-24T08:17:48Z) - Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement [92.61557711360652]
Language models (LMs) often fall short on inductive reasoning, despite achieving impressive success on research benchmarks.
We conduct a systematic study of the inductive reasoning capabilities of LMs through iterative hypothesis refinement.
We reveal several discrepancies between the inductive reasoning processes of LMs and humans, shedding light on both the potentials and limitations of using LMs in inductive reasoning tasks.
arXiv Detail & Related papers (2023-10-12T17:51:10Z) - Towards LogiGLUE: A Brief Survey and A Benchmark for Analyzing Logical Reasoning Capabilities of Language Models [56.34029644009297]
Large language models (LLMs) have demonstrated the ability to overcome various limitations of formal Knowledge Representation (KR) systems.
LLMs excel most in abductive reasoning, followed by deductive reasoning, while they are least effective at inductive reasoning.
We study single-task training, multi-task training, and "chain-of-thought" knowledge distillation fine-tuning technique to assess the performance of model.
arXiv Detail & Related papers (2023-10-02T01:00:50Z) - A Survey of Imitation Learning: Algorithms, Recent Developments, and
Challenges [9.288673880680033]
imitation learning (IL) is a process where desired behavior is learned by imitating an expert's behavior.
This paper aims to provide an introduction to IL and an overview of its underlying assumptions and approaches.
It also offers a detailed description of recent advances and emerging areas of research in the field.
arXiv Detail & Related papers (2023-09-05T11:56:07Z) - Large Language Models are In-Context Semantic Reasoners rather than
Symbolic Reasoners [75.85554779782048]
Large Language Models (LLMs) have excited the natural language and machine learning community over recent years.
Despite of numerous successful applications, the underlying mechanism of such in-context capabilities still remains unclear.
In this work, we hypothesize that the learned textitsemantics of language tokens do the most heavy lifting during the reasoning process.
arXiv Detail & Related papers (2023-05-24T07:33:34Z) - Can Pretrained Language Models (Yet) Reason Deductively? [72.9103833294272]
We conduct a comprehensive evaluation of the learnable deductive (also known as explicit) reasoning capability of PLMs.
Our main results suggest that PLMs cannot yet perform reliable deductive reasoning.
We reach beyond (misleading) task performance, revealing that PLMs are still far from human-level reasoning capabilities.
arXiv Detail & Related papers (2022-10-12T17:44:15Z)
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.