Multi-bit watermarking embeds a message, typically an account identifier, into LLM output so that harmful text can be traced to its origin. We show an attack technique that allows to alter the watermarking message. This allows to, for example, exchange the embedded account ID to an arbitrary different one. The attacker...
Pawe{\l} Batorski, Przemys{\l}aw Spurek, Paul Swoboda· 0 citations
Agent harnesses require a low-latency guardrail model together with customizable audit policies. However, deploying an auto-regressive guardrail model remains challenging: such models incur high inference latency and are often poorly aligned with customized policies. To address these problems, we present Jev-Guard, a u...
Wenbin Hu, Huihao Jing, Haochen Shi et al.· 0 citations
We present SWE-MISBEHAVIOR, the first taxonomy and evaluation framework for diagnosing boundary-violating misbehaviors in coding agents. It contains 7.4K human-in-the-loop synthesized samples spanning three layers of agent action space: (i) Code Generation, (ii) File Management, and (iii) System Interaction. Across the...
Do Xuan Trong, Duc Anh Nguyen, Do Xuan Long et al.· 0 citations
We introduce Fish Audio Drama 3, an open-source speech generation model that turns text into directed performances, built on a 35B-parameter mixture-of-experts backbone that activates 3B parameters per token. It clones voices from multiple references, follows natural-language direction, revises a take when the next tur...
Da-Wei Han, Shi-Dong Li, Shi-Jia Liao et al.· 2 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
A model trained on readers'highlights can show a newcomer where earlier readers converged on a page, even on pages with few readers. A year of stronger language models suggests two upgrades: use them directly, or use them as teachers. We compare both with a third, more reader data, on one social highlighting platform,...
Modern conversational information access systems continuously extract user information from conversations to build user profiles for personalized retrieval. As user profiles accumulate over time, they inevitably become noisy, making effective user profile denoising a fundamental challenge. Existing personalized convers...
Yuchen Hui, Fengran Mo, Jia Ao Sun et al.· 0 citations
StateHarness is introduced, a runtime framework that maintains evolving project state without updating model parameters and shows that maintaining project state can improve long-horizon coding while introducing measurable execution and regression trade-offs.
Chuan Zou, Yu-Jun Zhou, Xiao-Nan Luo et al.· 0 citations
This work builds a minimal multi-agent harness from the ground up and traces this frontier by varying, one at a time, the workflow stage at which a lead delegates to its workers (planning, implementation, or verification), the models that form the team, and the number of workers.
Keenan Samway, Daniel D'Souza, Omar Darwiche Domingues et al.· 0 citations
As large language models are deployed behind increasingly sophisticated safety mechanisms, evaluating their robustness under realistic adversarial conditions becomes increasingly difficult and critical. Existing jailbreaking evaluations often rely on static prompts, limited interaction horizons, or lightly protected sy...
Md Mushfiqur Rahman, Tobias Rohde, R. Tripathi et al.· Conference on Empirical Meth...· 0 citations
In LLM agent organizations, shared records determine which facts are available for later decisions. A sender consults interaction histories before deciding whether to report an event. A delivery gap across histories does not show whose relationship drove the choice or whether the resulting record matters downstream. We...
Junxi Huang, Wenshuo Chen, Nuoxuan Li et al.· 0 citations
Serving stacks for large language models manage context through four recurring mechanisms: incremental edits to a growing context, branching and snapshotting for tree search, identification of reusable prefixes for KV-cache reuse, and encoding of repeated segments. Each mechanism is served today by a different speciali...
Muntaser M Syed, Ameerah Alsulami, Marius Silaghi· 0 citations
Scientific claims shared through social media platforms frequently reference research findings without explicitly linking to the corresponding scientific publications. Automatically retrieving the correct scientific source for such claims is a challenging multilingual retrieval problem involving semantic matching, para...
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
