Tag
This paper presents a modular multi-agent platform for adversarially stress-testing role-playing language agents, using a strategy-driven Interrogator Agent and automated Judging Agent to reveal cumulative behavioral failures across multi-turn dialogues. Experiments across three personas and LLM families show multi-strategy adversarial evaluation reduces robustness scores by 0.17-0.20 and identifies common failure patterns, with strong human alignment.
BOOKMARKS is a search-based memory framework for role-playing agents that actively maintains task-relevant story details through structured bookmarks, outperforming existing recurrent summarization methods.
HumanLLM presents a framework for benchmarking and improving LLM anthropomorphism by modeling psychological patterns as interacting causal forces, constructing 244 patterns from academic literature and 11,359 multi-pattern scenarios. The approach demonstrates that authentic human alignment requires cognitive modeling rather than shallow behavioral mimicry, with HumanLLM-8B outperforming larger models like Qwen3-32B on multi-pattern dynamics.