Presents SpatialScore benchmark for MLLM spatial reasoning, evaluates 49 models showing large human gap, and supplies SpatialCorpus plus SpatialAgent to improve performance.
Embodied llm agents learn to cooperate in organized teams
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Tool-using LLM agents can implement undetectable stegosystems, shifting the primary barrier to covert multi-agent collusion from technical feasibility to coordination without explicit agreement.
Waypoint-based bi-level planning with curriculum RLVR improves multi-robot task success rates in dense-obstacle benchmarks over motion-agnostic and VLA baselines.
TeamFusion uses per-member proxy agents and iterative structured discussions to generate more representative and consensual team deliverables than direct aggregation in open-ended tasks.
Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
A survey of emerging AI agent architectures that organizes single and multi-agent designs around reasoning, planning, tool use, communication, and reflection phases.
citing papers explorer
-
Tool Use Enables Undetectable Steganography in Multi-Agent LLM Systems
Tool-using LLM agents can implement undetectable stegosystems, shifting the primary barrier to covert multi-agent collusion from technical feasibility to coordination without explicit agreement.
-
Navigating the Clutter: Waypoint-Based Bi-Level Planning for Multi-Robot Systems
Waypoint-based bi-level planning with curriculum RLVR improves multi-robot task success rates in dense-obstacle benchmarks over motion-agnostic and VLA baselines.
-
TeamFusion: Supporting Open-ended Teamwork with Multi-Agent Systems
TeamFusion uses per-member proxy agents and iterative structured discussions to generate more representative and consensual team deliverables than direct aggregation in open-ended tasks.
-
To trust or not to trust: Attention-based Trust Management for LLM Multi-Agent Systems
Introduces six-dimension trustworthiness definition and attention-based A-Trust score with a TMS to improve LLM-MAS robustness against malicious or unreliable messages.
-
Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application
This survey categorizes agentic environments for LLMs by eight attributes and domains, introduces symbolic and neural synthesis paradigms with evaluation, and outlines four agent evolution pathways plus three environment evolution paradigms.
-
The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey
A survey of emerging AI agent architectures that organizes single and multi-agent designs around reasoning, planning, tool use, communication, and reflection phases.