archive
Every paper Pith has read. Search by title, abstract, or pith.
954 papers in cs.MA · page 1
-
CHRONOS unifies index decay, pricing and privacy in data markets
CHRONOS: Temporally-Aware Multi-Agent Coordination for Evolving Data Marketplaces
-
Agent beats baselines at text-guided 3D photo search
PhotoFlow: Agentic 3D Virtual Photography Missions
-
IRV needs Θ(n (log m)^2) communication bits
The Communication Complexity of Instant-Runoff Voting
-
Safety, liveness, fairness defined for quantitative argumentation
Safety, Liveness, and Fairness in Quantitative Argumentation Dialogues
-
ARMS learns shaping rewards in MARL without altering Nash equilibria
ARMS: Automatic Reward Shaping for Sparse-Reward Multi-Agent Reinforcement Learning
-
Control index lets static optimization size EMFF satellite arrays
Optimal Design Framework for Distributed Array Using Magnetically-Actuated Satellite Swarm
-
Modal logic still triggers Arrow impossibility on cyclic frames
Arrow-Type Impossibility for Genuinely Modal Judgments
-
Six LLM agents self-refine topology optimization
Self-Refining Topology Optimization via an LLM-Based Multi-Agent Framework
-
Generated card games expose jagged strategic skills in top LLMs
GENSTRAT: Toward a Science of Strategic Reasoning in Large Language Models
-
Multi-agent AI raises gardener confidence and trust scores
CultivAgents: Cultivating Relationship-Centered Multi-Agent Systems for Personalized Gardening
-
Bayesian debate pruning cuts LLM token costs by 61%
SVR-MAD: A Bayesian-Inspired Framework for Posterior-Guided Multi-Agent Debate
-
Three axes organize human edits to multi-agent LLM plans
How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning
-
Online calibration cuts foundation model errors 3-6x under shift
MARGIN: Runtime Confidence Calibration for Multi-Agent Foundation Model Coordination
-
KV cache guard cuts reconstruction leaks in multi-agent LLMs
LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
-
Multi-agent RL drones beat humans with half the collisions
Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
-
Decentralized dual pools cut agent-team regret to O(log T)
Self-Evolving Multi-Agent Systems via Decentralized Memory
-
Game model guides trauma teams to best outcome under limits
A Generalized Nash Equilibrium-Seeking Scheme for Trauma Resuscitation
-
Trial harnesses let AI agents turn outcomes into process updates
Sibyl-AutoResearch: Autonomous Research Needs Self-Evolving Trial-and-Error Harnesses, Not Paper Generators
-
Deep RL agent outperforms rules at O-RAN conflict resolution
ACCoRD: Actor-Critic Conflict Resolution with Deep learning for O-RAN xApps
-
Benchmarks reveal when AI coordination improves scientific inference
Cross-domain benchmarks reveal when coordinated AI agents improve scientific inference from partial evidence
-
Agriculture arises spontaneously in reinforcement learning agent societies
Emergence of agriculture in an artificial society of reinforcement learning agents
-
Event log becomes the agent for replayable and forkable runs
The Log is the Agent: Event-Sourced Reactive Graphs for Auditable, Forkable Agentic Systems
-
AI gives serious games real-time adaptive training
AI-Enabled Serious Games: Integrating Intelligence and Adaptivity in Training Systems
-
Evolved skills from traces solve hard Verilog tasks
Trace2Skill: Verifier-Guided Skill Evolution for Long-Context EDA Agents
-
This paper proposes combining self-reported arrival times with uncertain surveillance…
Secure Coordination for Vertiport Sequencing in Advanced Air Mobility
-
Local rerollouts fix unfair credit assignment in memory LLM agents
Memory-R2: Fair Credit Assignment for Long-Horizon Memory-Augmented LLM Agents
-
GNN approximates altruistic robot transfers for scaling teams
Learning Altruistic Collaboration in Heterogeneous Multi-Team Systems
-
EV charging models face fidelity tradeoffs across three layers
Planning, Scheduling, and Behavior in EV Charging Systems: A Critical Survey and Trilemma Framework
-
Profiler cuts email labeling costs by 150X with near-GPT quality
Argo: Efficient Importance Labeling for Enterprise Email Systems
-
LLMs turn technical privacy details into clear reports for workers
Transforming Privacy Artifacts into Accessible Reports for Non-Technical Stakeholders
-
Decoupled messages sustain MARL performance at low bandwidth
Decoupling Communication from Policy: Robust MARL under Bandwidth Constraints
-
Self-elicited reasoning and critic revision improve sarcasm detection
ProCrit: Self-Elicited Multi-Perspective Reasoning with Critic-Guided Revision for Multimodal Sarcasm Detection
-
Heartbeat protocol revokes AI swarm credentials within fixed window
Heartbeat-Bound Hierarchical Credentials: Cryptographic Revocation for AI Agent Swarms
-
AI simulator trains clinicians on disclosing medical errors
CandorMD: An AI-Assisted Audio Simulation and Feedback System for Training Clinicians for Medical Error Disclosure
-
TTR metrics unify priority and safety for aerial vehicle merging
Time-To-Reach Separation and Safety Filtering for Safe, Fair, and Efficient Multi-Agent Coordination
-
Intent-first V2V supports drone tactical separation in moderate densities
Intent-First Aerial V2V for Tactical Coordination and Separation: Protocol and Performance Under Density and Disturbance
-
State management beats workspace isolation in multi-agent tasks
Multi-agent Collaboration with State Management
-
Reasoning and verification fix most multi-agent communication failures
What Do Agents Communicate? Characterizing Information Exchange in Multi-Agent Systems
-
Agentic AI coding improves with structured verification loops
Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development
-
SVD reduces multi-dimensional matching to fast one-dimensional optimization
Multi-Dimensional Matching in Market Design
-
Protocol wraps agent outputs in four-type verifiable attestations
Pramana: A Protocol-Layer Treatment of Claim Verification in Autonomous Agent Networks
-
Skills add almost no value to cybersecurity agents with rich tool feedback
When Skills Don't Help: A Negative Result on Procedural Knowledge for Tool-Grounded Agents in Offensive Cybersecurity
-
Complexity mapped for equilibria in multiplayer graph games
Equilibria in Multiplayer Graph Games: An Algorithmic Study
-
Coordinated LLM agents shift population beliefs in simulations
LLM Agents Make Collective Belief Dynamics Programmable: Challenges and Research Directions
-
Dynamic placement over three options cuts deadline misses in robot pipelines
DAG-Based QoS-Aware Dynamic Task Placement for Networked Multi-Stage Control Pipelines
-
Memory RL agent self-corrects complex CAD models
Memory-Augmented Reinforcement Learning Agent for CAD Generation
-
Multi-agent LLM framework hits 97 percent task completion on engineering benchmarks
EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design
-
Architecture lets AI agents break rules legitimately when justified
PAVE: A Cognitive Architecture for Legitimate Violation in Generative Agent Societies
-
STAR-PólyaMath hits perfect scores on Putnam and IMO
STAR-P\'olyaMath: Multi-Agent Reasoning under Persistent Meta-Strategic Supervision
-
Stake-weighted votes approximate power to ownership in expectation
Swimming with Whales: Analysis of Power Imbalances in Stake-Weighted Governance