token consumption

4 papers

• CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning
• Let LRMs Break Free from Overthinking via Self-Braking Tuning
• NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
• Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval