Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

arXiv:2609.01466 · cs.AI · Submitted 2026-09-01 · Read on arXiv

cs.AI

Submitted: 2026-09-01

Updated: 2026-09-01

Terminology

• Trace — 49× in this paper · explained in 2 episodes
• Accuracy — 12× in this paper · explained in 1 episode
• Benchmark — 11× in this paper · explained in 2 episodes
• Provenance — 7× in this paper · explained in 3 episodes
• Aggregation — 5× in this paper · explained in 1 episode
• AI Agents — 3× in this paper · explained in 2 episodes
• Agent Memory — 2× in this paper · explained in 1 episode
• LLM judge — 2× in this paper · explained in 2 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Agentic Task — 1× in this paper · explained in 1 episode
• Agentic Tasks — 1× in this paper · explained in 1 episode
• Benchmarking — 1× in this paper · explained in 3 episodes
• Consistency — 1× in this paper · explained in 3 episodes
• Core — 1× in this paper · explained in 2 episodes
• Deferral — 1× in this paper · explained in 2 episodes
• Elias — 1× in this paper · explained in 2 episodes
• Fidelity — 1× in this paper · explained in 2 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Robustness — 1× in this paper · explained in 5 episodes
• Thinking mode — 1× in this paper · explained in 2 episodes
• Verification — 1× in this paper · explained in 2 episodes

Sources

• The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
• HiAgent: Hierarchical Working Memory Management for Solving Long-Horizon Agent Tasks with Large Language Model
• Scaling Long-Horizon LLM Agent via Context-Folding
• ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
• ACON: Optimizing Context Compression for Long-horizon LLM Agents
• AgentFold: Long-Horizon Web Agents with Proactive Context Management
• LongSeeker: Elastic Context Orchestration for Long-Horizon Search Agents
• SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
• LLMs Get Lost In Multi-Turn Conversation
• Agentic Context Engineering: Evolving Contexts for Self-Improving Language Models
• Mem0: Building Production-Ready AI Agents with Scalable Long-Term Memory
• MemGPT: Towards LLMs as Operating Systems
• Zep: A Temporal Knowledge Graph Architecture for Agent Memory
• The OpenHands Software Agent SDK: A Composable and Extensible Foundation for Production Agents
• Don't Break the Cache: An Evaluation of Prompt Caching for Long-Horizon Agentic Tasks
• LOCA-bench: Benchmarking Language Agents Under Controllable and Extreme Context Growth
• Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
• LLM Agents Are Latent Context Managers: Eliciting Self-Managed Context via State Proprioception
• ESAA: Event Sourcing for Autonomous Agents in LLM-Based Software Engineering
• PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
• VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection