26 papers
Moral Safety in LLMs: Exposing Performative Compliance with Puzzled Cues
Mohammadamin Shafiei, Shuyue Stella Li, Yulia Tsvetkov
As large language models take on morally consequential roles in healthcare, legal, and hiring contexts, we need to examine whether their ethical behaviors are genuine or superficia…
Multilingual Reasoning Cascades Need More Context
Arnav Mazumder, Dengjia Zhang, Shuyue Stella Li +2
Translation cascades for reasoning translate the query from another language to English, reason in English, and translate the answer back to the original language. This is a compet…
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Jundong Xu, Qingchuan Li, Jiaying Wu +11
Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deploymen…
RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
Zhiyuan Zeng, Hamish Ivison, Yiping Wang +14
We introduce Reinforcement Learning (RL) with Adaptive Verifiable Environments (RLVE), an approach using verifiable environments that procedurally generate problems and provide alg…
StructBreak: Structural Cognitive Overload-Induced Safety Failures in MLLMs
Yang Luo, Xinran Liu, Tiantian Ji +3
Multimodal Large Language Models (MLLMs) excel at structural reasoning yet suffer from a sharp logical brittleness in structural consistency. We term this phenomenon Structural Cog…
ShadowMerge: A Novel Poisoning Attack on Graph-Based Agent Memory via Relation-Channel Conflicts
Yang Luo, Zifeng Kang, Tiantian Ji +4
Graph-based agent memory is increasingly used in LLM agents to support structured long-term recall and multi-hop reasoning, but it also creates a new poisoning surface: an attacker…