Who May Overrule the Agent? Evidence-Gated Authority in LLM Review Institutions
cs.AI, cs.MA
Submitted: 2026-09-12
Updated: 2026-09-12
Terminology
Sources
- The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
- Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?
- Minority Sentinel: When to Overturn Majority Voting in Multi-Agent LLM Debates
- Large Language Models Cannot Self-Correct Reasoning Yet
- AI safety via debate
- Self-Refine: Iterative Refinement with Self-Feedback
- Self-critiquing models for assisting human evaluators
- Trust but Verify: Prover-Verifier Deliberation for Selective LLM Prediction
- Group Perspective Matters: Regulating Debate Relationships Can Mitigate Blind Conformity in Multi-Agent Debate
- Qwen3 Technical Report
- An Electoral Approach to Diversify LLM-based Multi-Agent Collective Decision-Making
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- 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
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents