DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents
cs.AI
Submitted: 2026-09-23
Updated: 2026-09-23
Terminology
Sources
- ReAct: Synergizing Reasoning and Acting in Language Models
- MemGPT: Towards LLMs as Operating Systems
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- Distilling the Knowledge in a Neural Network
- Unifying distillation and privileged information
- ForesightKV: Optimizing KV Cache Eviction for Reasoning Models by Learning Long-Term Contribution
- Git Context Controller: Manage the Context of LLM-based Agents like Git
- Scaling Long-Horizon LLM Agent via Context-Folding
- AgentFold: Long-Horizon Web Agents with Proactive Context Management
- Chain of Draft: Thinking Faster by Writing Less
- Consistent Individualized Feature Attribution for Tree Ensembles
- Language Models with Conformal Factuality Guarantees
- Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
- Self-Compacting Language Model Agents
- Self-GC: Self-Governing Context for Long-Horizon LLM Agents
- CoMem: Context Management with A Decoupled Long-Context Model
- SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
- SWE-Pruner: Self-Adaptive Context Pruning for Coding Agents
- ACM: Agentic Context Management for Long Horizon Tasks
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