This work extends GOODLIAR from a single-turn attack to a multi-turn one and test two algorithms: a multi-turn variant of GOODLIAR’s DA-ILQL, an offline RL method with on-policy data aggregation, and a Proximal Policy Optimization (PPO) attacker, which is adopted because its per-turn rewards better match a multi-turn conversation.
Knowledge Distillation is a widely adopted technique in the training and fine-tuning of large language models (LLMs) enabling transfer of structured information and functional behavior from a large teacher model to a smaller student model while significantly reducing computational costs. However, as the use of distillation increases in both scale and complexity it raises an important question about what kind of knowledge is really transferred from the teacher model. In this work, we argue that apart from the functional knowledge, student models also learn behavioral patterns, specifically how a model represents its own identity raising concerns about output homogeneity, model biases, and accountability. To address this challenge, we introduce STEMMA, a multi-modal and multi-agent framework in which role specific agents collaboratively probe self identification behavior in different models. We also contribute a set of adversarial prompts designed manually to evaluate identity consistency in LLMs. Our results show that to an extent most models are vulnerable to inconsistencies in self-representations.
It is suggested that even subtle objective misalignment can profoundly affect collective decision-making, highlighting the need for effective mitigation strategies for LLM-based multi-agent systems.
A knowledge-verified benchmark that first confirms through a neutral probe that an agent knows a user's entitlement, and then evaluates whether it makes false claims once an incentive to deny that entitlement is introduced, which reduces the confound between lying and not knowing and enables more rigorous auditing and steering of agent honesty.
Zheyuan Liu, Weiliang Zhao, Xiangchi Yuan et al.· 0 citations
The LLM-as-a-Judge paradigm has emerged as a scalable alternative to human evaluation. However, single-model judges are limited by their inherent model biases, while multi-agent evaluation protocols that mitigate this through diverse deliberation are prohibitively expensive at inference time. To this end, we propose \textbf{\modelname}, which equips a compact \underline{Judge} model with multi-agent \underline{Panel} deliberation capability. Specifically, we first train on panel deliberation traces from an ensemble of strong evaluators, capturing structured patterns of discussion, disagreement, and resolution. To further improve judgment quality beyond SFT, we introduce \textit{AdaReward}, an adaptive multi-reward RL algorithm that dynamically rebalances reward component weights as different objectives saturate at different rates during RL training. For practical deployment, we further design a lightweight domain specialization module for rapid adaptation to new evaluation domains with few hundred labeled samples. As a result, (i) \textit{Novel}: the first framework to equip a single compact judge with multi-agent panel deliberation capability at single-model inference cost; (ii) \textit{Effective \&Reliable}: JudgePanel with a 14B backbone outperforms judge-specialized models up to 70B across four evaluation benchmarks, demonstrates strong position consistency, and rapidly specializes to new domains with few hundred samples.
Y. Qian, Shinan Zhang, Huan Song et al.· 0 citations
This work proposes AgentOPSD, a critic-free, recursive method for turn-level credit assignment in agentic reinforcement learning that aggregates token-level teacher-student log-probability gaps into turn-level evidence and recursively updates a Bayesian belief state in log-odds space.
Zi-Han Wang, Zhengxi Lu, Zhiyuan Yao et al.· 1 citation
An auditable framework is built that maintains an external belief state over hidden roles, logs belief updates and belief-action deviations as structured evidence, and supports a defensive offline improvement loop that reviews bad cases before any strategy change.
Yuanpeng Gao, Jiangyi Yang, Yao Zhao et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
