Geometry of Divergence: Tracking Hidden-State Trajectories for Adaptive Multi-Turn Reasoning
cs.AI, cs.CL
Submitted: 2026-08-31
Updated: 2026-08-31
Terminology
Sources
- $\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment
- INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
- Do NOT Think That Much for 2+3=? On the Overthinking of o1-Like LLMs
- The Danger of Overthinking: Examining the Reasoning-Action Dilemma in Agentic Tasks
- When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
- Do LLMs Know about Hallucination? An Empirical Investigation of LLM's Hidden States
- The Llama 3 Herd of Models
- Language Models (Mostly) Know What They Know
- Semantic Entropy Probes: Robust and Cheap Hallucination Detection in LLMs
- LLMs Get Lost In Multi-Turn Conversation
- AdaCoT: Pareto-Optimal Adaptive Chain-of-Thought Triggering via Reinforcement Learning
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
- A Survey of Context Engineering for Large Language Models
- Qwen3 Technical Report
- $\tau$-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains
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