Self-improving embodied agents are increasingly being developed and compared on robot simulation benchmarks. Several recent works expose the benchmark's success criteria to the learning agent, a practice we call Criteria Exposure (CE). These criteria, originally written to verify policies trained by imitation learning,...
Wenbo Huang, Jianxin Bi, Shunyu Yang et al.· 0 citations
Large language models (LLMs) are increasingly used in biomedical and cognitive neuroscience, but their ability to reason reliably over heterogeneous knowledge graphs (KGs) remains unclear. We benchmark five LLMs (GPT-5.1, Gemini 2.0 Pro, Llama 3, Qwen, and BioGPT) across five KGs: DrugBank, NeuroSynth, Cognitive Atlas,...
Ali Sarabadani, Kheirolah Rahsepar Fard, Tahereh Jeirani· 0 citations
Reward machines (RMs) have been proposed as a reward formulation in reinforcement learning (RL) to capture non-Markovian tasks where credit assignment depends on history. By representing reward functions as automata, RMs expose the task's temporal structure and allow such rewards to be handled within a Markovian framew...
Roko Parac, Christos Ziakas, Leo Ardon et al.· 0 citations
We study token dynamics in deep Mamba models, with a particular focus on the attracting role of the first token. Unlike attention mechanisms, where token interactions are governed by positive scalar coefficients, Mamba dynamics involve full matrix-valued interaction coefficients with no positivity or definiteness guara...
Trinh T. Nguyen, Minh-Khoi Nguyen-Nhat, Duy-Tung Pham et al.· 0 citations
Reach audiences
Advertise in front of researchers, engineers, and readers.
Contextual integrity (CI) holds that appropriate information flow depends on context-specific norms. The same disclosure may be appropriate in one context and inappropriate in another. We build a generative model of contextual integrity to study information sharing through simulated conversations. Two actors played by...
Omer Ebead, Claude Formanek, Joel Z. Leibo· 0 citations
Neural theorem proving increasingly uses retrieved premises and project context to support proof generation. Evaluating these resources requires measuring the advantage of target-selected declarations over comparable alternatives and how this advantage depends on training. We introduce LeanContext, a benchmark of 129,8...
Hang Zhang, Qihao Ye, Litong Liu et al.· 0 citations
Multimodal language models can simulate different observers, yet it remains unclear how assigned perspectives reshape their internal representations and whether these changes govern their judgements. Here, we investigate the representational geometry of persona-conditioned visual interestingness in Qwen3-VL-8B-Instruct...
Mathis Immertreu, Fitim Abdullahu, Thomas Kinfe et al.· 0 citations
Wind farm power control can help the system maintain balance and avoid blackouts. In Europe, this can be achieved through implicit balancing, where a wind farm adjusts its power setpoint in anticipation of the imbalance price using information published by the Transmission System Operator. Thereby, the wind farm helps...
Max Bruninx, Timothy Verstraeten, Jan Decuyper et al.· 0 citations
Large language models (LLMs) often present synthesized answers without making their supporting evidence easy to inspect. We study how features of these answers relate to users' subsequent accepting, checking, and challenging in 489,283 assistant-user response pairs from ShareChat and WildChat. Broad attribution languag...
Complex problems with limited context, such as claims, require a means to obtain additional knowledge necessary for solution reasoning. We propose a multi-agent framework, SMART, to obtain knowledge through capturing the implicit state of participating entities in a problem context. SMART curates the state knowledge as...
How would we know whether a machine truly understands the world? We argue that one key capability is \textit{observational theory learning}: acquiring reusable theories from pure observations and applying them to new situations. Current visual reasoning benchmarks focus primarily on the latter, presenting each task as...
Doojin Baek, Junyeob Baek, Mingyu Jo et al.· 0 citations
