archive
Every paper Pith has read. Search by title, abstract, or pith.
545 papers in cs.MA · page 1
-
APWA scales agent workflows by parallelizing non-communicating subproblems
APWA: A Distributed Architecture for Parallelizable Agentic Workflows
-
Multi-agent LLMs cut reservoir mismatch by up to 95%
Multi-Agentic Approach for History Matching of Oil Reservoirs
-
RL prompter lifts frozen LLM reasoning from 55% to 90%
Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience
-
Data-augmented starts cut exploitability in hard-to-explore games
Data-Augmented Game Starts for Accelerating Self-Play Exploration in Imperfect Information Games
-
Entangled QMARL agents near 0.85 win rate in CHSH game
Quantum Advantage in Multi Agent Reinforcement Learning
-
Mock agents hide real paths during multi-agent planning
Privacy Preserving Multi Agent Path Finding
-
ProtoMedAgent reaches 91.2% faithfulness in clinical reports
ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows
-
LLM framework unifies macro and micro economic simulations
EconAI: Dynamic Persona Evolution and Memory-Aware Agents in Evolving Economic Environments
-
SkillOps is a plug-in framework that maintains LLM agent skill libraries by representing…
SkillOps: Managing LLM Agent Skill Libraries as Self-Maintaining Software Ecosystems
-
Unweighted fuzzy ranking keeps decisions consistent without weights
Unweighted ranking for value-based decision making with uncertainty
-
LLMs show recall-safety tradeoffs on real ICU data
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
-
Metric-space protocol lets communities self-amend constitutions in polynomial time
Constitutional Governance in Metric Spaces
-
One rule unifies voting, proposals and constitutional amendment in metric spaces
Constitutional Governance in Metric Spaces
-
ED digital twin replicates real-world intervention outcomes
Multi-Agent Systems in Emergency Departments: Validation Study on a ED Digital Twin
-
Graph links convergent claims from multiple innovation methods
IdeaForge: A Knowledge Graph-Grounded Multi-Agent Framework for Cross-Methodology Innovation Analysis and Patent Claim Generation
-
Diffusion initializer lifts multi-agent path success to 95.8 percent
Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention
-
Contrastive rollouts assign credit to individual agents in LLM teams
CANTANTE: Optimizing Agentic Systems via Contrastive Credit Attribution
-
Conventions enable composition of policies for multiple omega-regular goals
Decoupled Planning for Multiple Omega-Regular Objectives
-
This paper introduces DESBench
When Does Hierarchy Help? Benchmarking Agent Coordination in Event-Driven Industrial Scheduling
-
Gradient selection finds weakest messages to attack multi-agent comms
Finding the Weakest Link: Adversarial Attack against Multi-Agent Communications
-
Multi-agent system automates VC due diligence
A Multi-Agent Orchestration Framework for Venture Capital Due Diligence
-
Shapley values fairly assign responsibility in stochastic games
Counterfactual Reasoning for Causal Responsibility Attribution in Probabilistic Multi-Agent Systems
-
The paper introduces Dual-Ordering Prioritized Planning (DOPP)
Conveyor Parcel Routing with Order-Contiguous Arrivals
-
Swarms form sub-goal chains to transport objects past obstacles
Occlusion-Based Object Transportation Around Obstacles With a Swarm of Miniature Robots
-
Scale separates mechanistic explanation from reproduction in LLM models
Mechanism Plausibility in Generative Agent-Based Modeling
-
Electricity fairness reduced to k-times bin packing
Time and Supply Fairness in Electricity Distribution using $k$-times bin packing
-
Synthetic dataset benchmarks AI for swim coaching
Synthesizing the Expert: A Validated Multimodal Dataset for Trustworthy AI-Assisted Swimming Coaching
-
Groups modeled as dynamical systems via behavioral fields
BEHAVE: A Hybrid AI Framework for Real-Time Modeling of Collective Human Dynamics
-
CHAL turns multi-agent debate into gradient belief optimization
CHAL: Council of Hierarchical Agentic Language
-
Bellman-target correction lets agents follow mid-task instructions
Macro-Action Based Multi-Agent Instruction Following through Value Cancellation
-
Tabular model predicts AI agents' moves from 16 past games
Predicting Decisions of AI Agents from Limited Interaction through Text-Tabular Modeling
-
Population summaries cut multi-agent forecast errors 16-19%
Ready from Day 1: Population-Aware Coordination for Large-Scale Constrained Multi-Agent Systems
-
Events let agents switch roles on demand without losing reward
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
-
Events trigger dynamic role switches in multi-agent RL
Events as Triggers for Behavioral Diversity in Multi-Agent Reinforcement Learning
-
Compromised AI provider enables data theft and policy bypass
Attacks and Mitigations for Distributed Governance of Agentic AI under Byzantine Adversaries
-
AI agents gain revisability by keeping durable intermediate artifacts
Intermediate Artifacts as First-Class Citizens: A Data Model for Durable Intermediate Artifacts in Agentic Systems
-
Benchmark finds skills expose agents to unsafe attacks
SkillSafetyBench: Evaluating Agent Safety under Skill-Facing Attack Surfaces
-
Estimator adapts TD(lambda) for superior multi-agent RL
Adaptive TD-Lambda for Cooperative Multi-agent Reinforcement Learning
-
Critic and generator agents iteratively refine research outlines
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
-
Seminar sets six research priorities for agents and software engineering
A Research Agenda on Agents and Software Engineering: Outcomes from the Rio A2SE Seminar
-
State blocking trains agents for unseen partners
Shaping Zero-Shot Coordination via State Blocking
-
Agent graph curvature flags herding 272 steps before prices
GeomHerd: A Forward-looking Herding Quantification via Ricci Flow Geometry on Agent Interactive Simulations
-
LLM hierarchy boosts UAV efficiency by 14% and throughput by 25%
Hierarchical LLM-Driven Control for HAPS-Assisted UAV Networks: Joint Optimization of Flight and Connectivity
-
Distance rule makes unlabeled MAPF feasibility PSPACE-complete
Distance-Constrained Unlabeled Multi-Agent Pathfinding
-
Agents carry explicit permissions that stay consistent across systems
Digital Identity for Agentic Systems: Toward a Portable Authorization Standard for Autonomous Agents
-
Successor spectra rank LLM topologies by three failure modes
Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologies
-
Spectral properties of successor representations rank multi-agent LLM communication…
Predictive Maps of Multi-Agent Reasoning: A Successor-Representation Spectrum for LLM Communication Topologies
-
Learned contracts let Senders extract surplus despite misaligned incentives
Information and Contract Design for Repeated Interactions between Agents with Misaligned Incentives
-
PIVOT refines trajectories to cut LLM agent execution failures
PIVOT: Bridging Planning and Execution in LLM Agents via Trajectory Refinement
-
Topology sets when multi-agent laws can be recovered from trajectories
Multi-Agent System Identification with Nonlinear Sheaf Diffusion