Papers with AI agent
Debug Smarter, Not Harder: AI Agents for Error Resolution in Computational Notebooks (2024.emnlp-demo)
Copied to clipboard
| Challenge: | Existing tools for bug-fixing in computational notebooks are tuned for script programming and struggle with non-linear notebooks. |
| Approach: | They propose an agentic system capable of exploring a notebook environment by interacting with it. |
| Outcome: | The proposed system explores a notebook environment and integrates it into JetBrains' datalore service. |
Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback (2024.findings-eacl)
Copied to clipboard
| Challenge: | In many approaches to Natural Language Processing tasks, language is inherently interactive. |
| Approach: | They propose to use human-AI collaboration to improve human-human interaction by providing feedback that the agent can understand and utilize. |
| Outcome: | The proposed task is an interactive grounded language understanding task in a MineCraft-like world. |
Ensemble of MRR and NDCG models for Visual Dialog (2021.naacl-main)
Copied to clipboard
| Challenge: | BLEU scores favor correct syntax over semantics. |
| Approach: | They propose a non-parametric ranking method that integrates the ranks of two strong MRR and NDCG models into a single ranking that excels on both metrics. |
| Outcome: | The proposed model can keep the MRR and NDCG models state-of-the-art and the NDGC models state of the art. |
Attend What You Need: Motion-Appearance Synergistic Networks for Video Question Answering (2021.acl-long)
Copied to clipboard
| Challenge: | Recent advances in natural language processing and computer vision have made significant progress in artificial intelligence (AI). |
| Approach: | They propose Motion-Appearance Synergistic Networks which embed cross-modal features grounded on motion and appearance information and selectively utilize them depending on the question’s intentions. |
| Outcome: | The proposed network achieves state-of-the-art on the TGIF-QA and MSVD-QA datasets and qualitatively analyzes the results. |
Spatial-Agent: Agentic Geo-spatial Reasoning with Scientific Core Concepts (2026.acl-long)
Copied to clipboard
| Challenge: | Existing LLM-based agents lack inherent spatial awareness, relying on web search or text matching while hallucinating spatial relationships. |
| Approach: | They propose a spatial-based agent that can perform real-world geospatial computations . they use natural-language questions to parse into executable workflows based on geoFlow Graphs - directed acyclic graphs with nodes corresponding to spatial concepts and edges representing transformations. |
| Outcome: | The proposed agent outperforms existing baselines on MapEval-API and MapQA benchmarks while producing interpretable and executable geospatial workflows. |
Minimal Yet Big Impact: How AI Agent Back-channeling Enhances Conversational Engagement through Conversation Persistence and Context Richness (2024.findings-emnlp)
Copied to clipboard
| Challenge: | Increasing use of AI agents in conversational services highlights the importance of back-channeling (BC) as an active listening strategy to enhance conversational engagement. |
| Approach: | They conducted an experiment with 55 participants to evaluate conversational engagement using both quantitative and qualitative metrics. |
| Outcome: | The results show that the Todak_BC and TodAK_NoBC groups have significantly higher conversational engagement than the Todask_NoB. |