Agent Systems

Structurally Guided Task Decomposition in Spatial Navigation Tasks (Student Abstract) AAAI 2024 SUPER: Evaluating Agents on Setting Up and Executing Tasks from Research Repositories EMNLP 2024 Sustainability of Data Center Digital Twins with Reinforcement Learning AAAI 2024 SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering NeurIPS 2024 SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents NeurIPS 2024 Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control ICLR 2024 Synatra: Turning Indirect Knowledge into Direct Demonstrations for Digital Agents at Scale NeurIPS 2024 Synthetic Arabic Medical Dialogues Using Advanced Multi-Agent LLM Techniques ACL 2024 T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration AAAI 2024 Tailoring with Targeted Precision: Edit-Based Agents for Open-Domain Procedure Customization ACL 2024 Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests EACL 2024 TaskBench: Benchmarking Large Language Models for Task Automation NeurIPS 2024 Task-Oriented Human-Object Interactions Generation With Implicit Neural Representations WACV 2024 Task Planning for Visual Room Rearrangement under Partial Observability ICLR 2024 Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use EMNLP 2024 Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents ACL 2024 TETRIS: Towards Exploring the Robustness of Interactive Segmentation AAAI 2024 Text2DB: Integration-Aware Information Extraction with Large Language Model Agents ACL 2024 Text2Reward: Reward Shaping with Language Models for Reinforcement Learning ICLR 2024 The Curse of Diversity in Ensemble-Based Exploration ICLR 2024 The Effective Horizon Explains Deep RL Performance in Stochastic Environments ICLR 2024 The motion planning neural circuit in goal-directed navigation as Lie group operator search NeurIPS 2024 The SETU-ADAPT Submission for WMT 24 Biomedical Shared Task EMNLP 2024 The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models ICLR 2024 TimeArena: Shaping Efficient Multitasking Language Agents in a Time-Aware Simulation ACL 2024