Active Neural Matter: A Finite-Window Response Framework for Physical Systems and Distributed AI Workflows
cs.LG, cond-mat.stat-mech, cs.AI, cs.DC, physics.app-ph
Submitted: 2026-10-10
Updated: 2026-10-10
Code: https://github.com/allenai/scifact
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Qwen2.5 Technical Report
- Physics of Agents: Statistical Mechanics Predicts Collective Behavior of AI Agents
- Blind Construction of Optimal Nonlinear Recursive Predictors for Discrete Sequences
- ReAct: Synergizing Reasoning and Acting in Language Models
- Toolformer: Language Models Can Teach Themselves to Use Tools
- AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
- GAIA: a benchmark for General AI Assistants
- Field-Theoretic Memory for AI Agents: Continuous Dynamics for Context Preservation
- Traceability and Accountability in Role-Specialized Multi-Agent LLM Pipelines
- AgentTrace: Causal Graph Tracing for Root Cause Analysis in Deployed Multi-Agent Systems
- GRADE: Graph Representation of LLM Agent Dependency and Execution
- Adaptive Influence Graphs for Failure Attribution in Multi-Agent Systems
- EDGE: Error Dependency Graph-Guided Multi-Error Attribution in Multi-Agent LLM Systems
- DoVer: Intervention-Driven Auto Debugging for LLM Multi-Agent Systems
- When "Must" Becomes "Maybe": Erosion of Workflow Constraints in LLM Agent Handoffs
- When Errors Become Memories: Causal Pathway Tracing in Multi-Turn Memory-Augmented LLMs
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks