Phantom Merge: When Your Large Language Model Agents Pick One but Tell You About Another
cs.AI, cs.CL
Submitted: 2026-10-12
Updated: 2026-10-12
Code: https://github.com/LabRAI/PhantomMerge
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- Mind2Web: Towards a Generalist Agent for the Web
- On the Failure of Latent State Persistence in Large Language Models
- Entity Tracking in Language Models
- FHIR-AgentBench: Benchmarking LLM Agents for Realistic Interoperable EHR Question Answering
- AgentBench: Evaluating LLMs as Agents
- ShoppingBench: A Real-World Intent-Grounded Shopping Benchmark for LLM-based Agents
- Qwen3 Technical Report
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