Plans Fade Fast: Why Context Management Is Load-Bearing for LLM Agents
cs.AI, cs.CL
Submitted: 2026-06-22
Updated: 2026-10-12
Terminology
Sources
- Eliciting Latent Predictions from Transformers with the Tuned Lens
- Discovering Latent Knowledge in Language Models Without Supervision
- Tracing the Traces: Latent Temporal Signals for Efficient and Accurate Reasoning
- The Llama 3 Herd of Models
- Inner Monologue: Embodied Reasoning through Planning with Language Models
- LLMs Get Lost In Multi-Turn Conversation
- Reasoning Models Know When They're Right: Probing Hidden States for Self-Verification
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- When Agents Disagree With Themselves: Behavioral Consistency as an Uncertainty Signal for LLM Agents
- Confident and Wrong: Silent Semantic Failures in Coding Agents
- Qwen3 Technical Report
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- Improving Instruction-Following in Language Models through Activation Steering
- Steering Language Models With Activation Engineering
- From Reasoning to Answer: Empirical, Attention-Based and Mechanistic Insights into Distilled DeepSeek R1 Models
- ReasonIF: Large Reasoning Models Fail to Follow Instructions During Reasoning
- Effectively Controlling Reasoning Models through Thinking Intervention
- Retrieval Head Mechanistically Explains Long-Context Factuality
- HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering
- ReAct: Synergizing Reasoning and Acting in Language Models
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