The paper introduces Multi-agent Undercover Gaming (MUG), a protocol that extends the Multi-Agent Debate (MAD) framework to address hallucinations in large language models. MUG reframes MAD as a detection task for ‘undercover’ agents—those that hallucinate—by using multimodal counterfactual tests that modify reference images to reveal hallucinations. The approach enhances factual verification, cross‑evidence reasoning, and active discussion among agents, aiming to improve reliability in multimodal reasoning.
arXiv:2605.27068v2 Announce Type: replace-cross Abstract: Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Mo...
DREAM (Dynamic Resolution Assignment For Multimodal Multi-Agent Debate) enhances multimodal multi-agent debate by dynamically assigning each agent the optimal visual resolution through a zero-shot probe round that measures uncertainty with Average Normalized Log-Likelihood. It also introduces Uncertainty-Guided Rollback Aggregation to mitigate groupthink by tracking and restoring low-uncertainty answers that are overridden by group pressure. Across six multimodal datasets, DREAM improves the accuracy-token trade-off by 1.5–3.2% over existing baselines without requiring dataset-specific tuning.
arXiv:2510. 20963v2 Announce Type: replace Abstract: Multi-agent debate (MAD) was proposed as a promising approach for ensembling the wisdom of multiple large language models (LLMs) to improve reasoning and provide effective supervision to superhuman LLMs.
arXiv:2601. 02854v2 Announce Type: replace Abstract: As an agent-level reasoning and coordination paradigm, Multi-Agent Debate (MAD) orchestrates multiple agents through structured debate to improve answer quality and support complex reasoning.
arXiv:2608. 12877v1 Announce Type: new Abstract: Multi-hop fact verification, which verifies claims by reasoning over multiple pieces of evidence, is critical for combating misinformation on social media yet remains highly challenging.
arXiv:2604. 11741v2 Announce Type: replace Abstract: Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information.
arXiv:2601. 05746v2 Announce Type: replace Abstract: Recent years have witnessed the rapid development of Large Language Model-based Multi-Agent Systems (MAS), which excel at collaborative decision-making and complex problem-solving.
arXiv:2607. 14499v1 Announce Type: new Abstract: Multi-modal Large Language Models (MLLMs) have made substantial advances on benchmarks, yet their real-world effectiveness remains uncertain.
arXiv:2606. 29425v1 Announce Type: new Abstract: Existing multi-agent debate frameworks suffer from two critical limitations: they rely on static architectures where agent roles and coordination patterns are fixed at design time, and they require instantiating multiple model copies, incurring substantial computational overhead.
The paper introduces a text-based, multi-agent version of the board game Clue to test multi-step deductive reasoning in large language models (LLMs). Six LLM-based agents (GPT‑4o‑mini and Gemini‑2.5‑Flash) play turn‑based games, and a tool‑augmented approach uses a structured possibility matrix to convert implicit game state into explicit remaining possibilities, thereby offloading memory and deductive constraints from the agents. The study compares this tool‑augmented method against a baseline to assess its impact on reasoning quality and task success in a strategic reasoning environment.
arXiv:2505. 23399v2 Announce Type: replace Abstract: We propose GAM-Agent, a game-theoretic multi-agent framework for enhancing vision-language reasoning.
SocialReasonBench is a new video‑multiple‑choice QA benchmark designed to test socially grounded reasoning in interactive narrative videos. It uses branching gameplay footage from *Detroit: Become Human*, where player choices create alternative social outcomes that can be verified against the game’s script and flowchart. The benchmark includes seven reasoning dimensions—such as intent recognition, emotional empathy, moral dilemma, counterfactual reasoning, and causal antecedent—and employs a multi‑agent pipeline to curate clips, ground answer labels, and generate theory‑guided questions with diagnostic distractors.