arXiv:2605. 06605v2 Announce Type: replace Abstract: Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv Machine Learning.
arXiv:2510. 17947v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are improving at an exceptional rate.
arXiv:2605. 00123v3 Announce Type: replace Abstract: Safety trained large language models (LLMs) can often be induced to answer harmful requests through jailbreak prompts.
arXiv:2602. 16346v4 Announce Type: replace-cross Abstract: LLM-based agents execute real-world workflows via tools and memory.
arXiv:2606. 01738v1 Announce Type: cross Abstract: Multi-turn jailbreak attacks pose a growing threat to LLMs by exploiting conversational dynamics such as gradual escalation and cross-turn coordination.
arXiv:2510. 02422v4 Announce Type: replace-cross Abstract: Existing gradient-based jailbreak attacks typically optimize a fixed-length adversarial suffix toward a predefined target response with a static optimization strategy.
arXiv:2606. 19755v1 Announce Type: cross Abstract: Speculative inference accelerates large language model (LLM) decoding but provides no inherent safety guarantees.