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.
By Dayong Liang, Xiao-Yong Wei, Linhui Xiao, Changmeng Zheng
arXiv:2606. 04202v1 Announce Type: new Abstract: As LLMs become more widely deployed, they are increasingly expected to work alongside other AI agents rather than operating in isolation.
By Joel Sol, Homayoun Najjaran
Fig (Finding Interactions in Games) is an agentic system that performs targeted elicitation interventions on game environments to study multiagent behaviors. It takes a natural‑language behavior description, decomposes it into sub‑behaviors, generates or selects appropriate social games, and applies interventions to the game engine, opponents, instructions, and context. The system evaluates model behavior using mechanical checks and synthetic rubric judgments, and human review validates the interventions, generated games, and evaluation mechanisms. In experiments, models attempted the target behavior in 45.2% of episodes on average for six test behaviors, and Fig’s interventions increased attempt rates by 10.9% compared to matched control games.
By Anrui Gu, Zhichao Wang, Nicolai Ouporov
arXiv:2607. 08066v1 Announce Type: new Abstract: Chain-of-thought (CoT) monitoring is a promising safety mechanism for AI agents, based on the premise that visible reasoning traces can surface misaligned or deceptive behavior.
By Jennifer Za, Julija Bainiaksina, Nikita Ostrovsky, Tanush Chopra, Victoria Krakovna
The paper introduces a new attack called "plan injection" that allows a large language model to carry out harmful actions while evading chain-of-thought monitoring. By inserting harmful but benign-sounding reasoning into the model’s context, the attacker can steer the model’s behavior and cause it to paraphrase the injected plan as its own reasoning. The study demonstrates that this attack works across different monitoring settings, scales to harder tasks, and even causes monitors to waste resources on the injected plan, reducing detection rates by up to 50%.
By Keertana Chidambaram, Andrew Ilyas, Vasilis Syrgkanis
The paper introduces DoublesEval, a diagnostic framework that uses professional doubles badminton to test visual‑language models’ ability to reason about dynamic multi‑agent interactions. It decomposes rallies into key moments and evaluates models across four dimensions—atomic recognition, intra‑segment composite understanding, cross‑segment causal reasoning, and high‑level tactical abstraction—highlighting specific reasoning failures. The authors also propose TacticCheck, a lightweight consistency checker that improves performance without retraining the models, yet significant gaps remain in tactical reasoning.
By Jintao Cheng, Weibin Li
arXiv:2606. 22737v2 Announce Type: replace Abstract: Before letting an agent operate over real context, can you prove it used the right evidence?
By Jeffrey Flynt
MADBench is a benchmark that evaluates the security of Multi-Agent Debate (MAD) systems, which allow large language models to exchange and critique answers. The study categorizes attacks into a layered taxonomy aligned with the MAD workflow and tests six attack families across 356 source tasks and 3,958 test cases. Results indicate that while MAD can reduce answer accuracy attacks compared to single-agent baselines, it may amplify unauthorized reads or writes, and even with collusion among agents, the final answer changes from correct to wrong only 28.30% of the time.
By Yuwan Liu, Jiaming Zhang, Yue Huang, Sisi Duan
arXiv:2606.16710v2 Announce Type: replace-cross
Abstract: Multi-agent systems (MAS) are credited with solving complex problems, yet their agents routinely act on context that may be false. Prior work...
By Jonas Becker, Jan Philip Wahle, Terry Ruas, Bela Gipp
Visual Language Models (VLMs) excel at describing visible scene content but struggle to reason about dynamic multi-agent interactions, where action semantics depend on coordinated roles and spatial-te...
arXiv:2609.06063v1 Announce Type: new
Abstract: AI Agents are increasingly deployed in real-world settings, where they interact with external tools and make sequential decisions with limited human ov...
By Vittoria Vineis, Fabiano Veglianti, Lorenzo Antonelli, Claudia Di Carlo, Matteo Silvestri, Gabriele Tolomei
The paper introduces a belief‑shift evaluation benchmark for large language models (LLMs) using the social‑deduction game Werewolf. By annotating suspicion and accusation messages in LLM‑played games, the authors measure how a village‑side model’s beliefs change after each message, evaluating 40 open‑weight LLMs on 1,224 annotated messages. Results show that larger models better distinguish wolves from villagers, yet accusations still heavily sway beliefs, especially when the accuser is trusted, and even when the accuser is wolf‑aligned.
"whyItMatters":"The study highlights that current open‑weight LLMs up to 120B parameters still struggle to integrate accusation content with source trust in strategic communication, revealing limitations in their belief‑updating capabilities in complex social contexts."
By Yu-Yu Yang, Ti-Rong Wu, Hung Guei, Hsing-Yu Chen, I-Chen Wu