Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus
cs.AI, cs.LG
Submitted: 2026-10-06
Updated: 2026-10-06
Terminology
Sources
- MemGPT: Towards LLMs as Operating Systems
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models
- Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures
- Context as a Tool: Context Management for Long-Horizon SWE-Agents
- Memory as Action: Autonomous Context Curation for Long-Horizon Agentic Tasks
- Towards Reliable Context Compression for Long-Horizon Agents: An Empirical Study of Execution Instability
- AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
- Which Agent Causes Task Failures and When? On Automated Failure Attribution of LLM Multi-Agent Systems
- The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
- How to Interpret Agent Behavior
- AI Agent Behavioral Science
- Doubly Robust Policy Evaluation and Learning
- Selective Classification for Deep Neural Networks
- Non-Determinism of "Deterministic" LLM Settings
- Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference
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
- Agents' Last Exam
- 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