Excited to announce seven papers accepted to EMNLP 2026, three to the main conference and four to Findings! Main conference: Who is the Agent to Blame?: localizing faithfulness and citation mistakes in agentic deep research. How Well Do Vision-Language Models Understand Movies?. FrankenReport: early exiting in long-form generation using expected value of computation. Findings: PragReST: self-reinforcing counterfactual reasoning for pragmatic language understanding. Balancing Faithfulness and Performance in Reasoning via Multi-Listener Soft Execution. A History-Aware Visually Grounded Critic for Computer Use Agents. Debug or Regenerate?: test-guided selection for LLM code repair.