When Can Agents Forget Their Reasoning? ICLR for Long-Horizon Agent Context Compression
cs.AI, cs.CV
Submitted: 2026-09-24
Updated: 2026-09-24
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- ContextBudget: Budget-Aware Context Management for Long-Horizon Search Agents
- Self-Consistency Improves Chain of Thought Reasoning in Language Models
- Chain Of Thought Compression: A Theoretical Analysis
- Self-Compacting Language Model Agents
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- MemGPT: Towards LLMs as Operating Systems
- SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
- ACM: Agentic Context Management for Long Horizon Tasks
- Understanding intermediate layers using linear classifier probes
- Training Large Language Models to Reason in a Continuous Latent Space
- Quiet-STaR: Language Models Can Teach Themselves to Think Before Speaking
- Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention
- Scaling Long-Horizon LLM Agent via Context-Folding
- ReSum: Unlocking Long-Horizon Search Intelligence via Context Summarization
- AgentFold: Long-Horizon Web Agents with Proactive Context Management
- Active Context Compression: Autonomous Memory Management in LLM Agents
- Self-GC: Self-Governing Context for Long-Horizon LLM 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