Background. A component replacement in a language-model agent changes an execution trajectory, potentially altering later observations, resource use, and recovery opportunities. Different evidence is needed to assess its task-level benefit and the contribution of local decision quality. Methods. This critical scoping r...
Multi-modal integrated sensing and communication (ISAC) enables environmental perception and reliable connectivity for intelligent wireless networks. Data-driven multi-modal ISAC models depend heavily on annotated real-world data to learn relationships across sensing and wireless observations, thereby constraining scal...
Yijie Bian, Kai Zhang, Wei Guo et al.· 0 citations
Corporate and investment banking teams use presentations to support credit decisions and advise clients on financing and transactions. Producing these decks requires reconciling financial data, tracing sources and turning analysis into a recommendation. We retrospectively study the development of an agentic harness com...
Ludovic Gibert, Matis Despujols, André Rochet· 0 citations
Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among several precursor sets for the same product, for example to preserve a particular motif. Recovering a recorded answer alone does not establish this ability to follow a...
Xuemin Chen, Xiaozhuang Song, Xinjian Zhao et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
When designing machine learning models, desirable properties are often in tension: improving one behavior can impair another, so task progress can depend on alleviating the conflict. LLM-based AutoResearch systems, which iteratively edit model code and retain edits based on scalar task-performance feedback, have largel...
Binqian Xu, Qiran Zou, Xiangbo Shu et al.· 0 citations
Scientific software presents a demanding test for computer-using agents based on visual language models (VLMs): completing a research workflow requires interpreting specialized interfaces, manipulating scientific objects, and producing verifiable results. We thus introduce OSWorld-Science, a benchmark and evaluation en...
Ding-Yuan Dai, He-Li Qi, Lei Liu et al.· 0 citations
Grammar-constrained generation guarantees syntactic validity, but can substantially degrade semantic quality when the model's preferred outputs are poorly aligned with the imposed grammar. This trade-off is particularly severe when the prompt is underspecified or the model has limited instruction-following ability. Bea...
Gabriele Tuccio, Antonino Furnari, Aldo Gangemi et al.· 0 citations
Exploratory reinforcement learning (RL) on an operating bus fleet is impractical,while policies trained only from historical data cannot acquire new experience. Hybrid Offline-and-Online (H2O) RL combines fixed target replay with simulator interaction, but the inexpensive online simulator can differ from the target in...
Large language models frequently fail to balance staying truthful with being supportive. They often exhibit sycophancy in responses to users, agreeing with false claims, offering unwarranted flattery, and giving advice skewed toward users'expressed views. In reality, sycophancy rarely happens in a single exchange; it m...
Sidharth Pulipaka, R. Binkytė, Ivaxi Sheth et al.· 0 citations
Chain-of-thought monitoring as an approach for AI oversight and control is threatened by the possibility of steganographic reasoning, where LLMs conceal their reasoning inside innocuous-looking text. Two neighbouring capabilities, steganographic messaging (passing a concealed message) and encoded reasoning (reasoning i...
Julian Schulz, Lukas F\"ulle, Rieke Fruengel· 0 citations
Latent communication enables multi-agent systems to exchange information directly in internal representation space, reducing the token, computation, and latency overhead of text-based communication. To this end, lightweight trainable links are introduced to map the sender's representations into the receiver's input spa...
M. Huzaifa, Sina Mavali, Thorsten Eisenhofer· 0 citations
Cooperative language-model agents must coordinate over long horizons and adapt to changing environments and to partners with unfamiliar conventions, yet existing agents map observations to actions without separating persistent coordination strategies from their tactical execution. We introduce OverForge, a training-fre...
Machine-learning networks can learn without detailed instructions from a designer. Those that do may offer insight into how the brain reorganizes itself during learning.
