Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2610.25916v2 Announce Type: replace-cross Abstract: As coding models and agent harnesses become more capable, reliable security verification is becoming a central bottleneck. Improving secure c...
arXiv:2610.26847v2 Announce Type: replace-cross Abstract: Long-horizon agents must learn heterogeneous capabilities from interleaved trajectories. Updating shared parameters to learn new capabilities...
Battle Drones is a browser‑based, Command & Conquer‑style real‑time strategy game that evolved through 12 major iterations, adding 3D models, varied terrain, random map generation, and both local and online multiplayer via audio synchronization. The game features nine buildings, seven ground vehicles, six aerial vehicles, and three infantry units, with fog of war, area‑effect weapons, and multiple play modes such as skirmish and last‑stand. The project showcases how AI‑assisted coding (primarily Claude) can accelerate game development and introduce innovative multiplayer mechanics using sound.
Simulation is a powerful tool for robotics, but building diverse, simulation-ready scenes at scale remains difficult. Reconstructing scenes from single images is a promising alternative, but visual si...
Clustered federated learning (CFL) can suffer from cluster collapse. In particular, under unfavorable initialization, early client assignments concentrate heterogeneous groups on one cluster model, wh...
LLM agents are commonly trained with RLVR, but the sparse nature of typical RLVR rewards makes credit assignment challenging, especially for long-horizon tasks. We propose Self-Credit, an end-to-end a...
Agent harnesses are executable code that specifies the prompts, tools, and control flow around a language model. A single global harness can struggle with heterogeneous tasks that require different ex...
Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. While modern MLLMs perform well...
Reasoning about fine-grained placement constraints, such as support and containment, is essential for realistic 3D scene creation. It remains a significant challenge for existing methods that rely on...
The article titled "Skill or MCP Server? Ask What Stops the LLM From Disobeying" discusses the concept of spec-driven test automation, specifically in the context of part 4 of a series. It explores how to prevent large language models from acting against intended instructions. The piece was originally published on Towards Data Science.
Voxtral 3 is Mistral AI’s voice‑agent SDK that enables real‑time speech processing in over 50 languages. It offers accurate transcription, emotionally expressive text‑to‑speech, and deep tool‑use capabilities. The SDK can be hosted in the EU or self‑deployed by users.
Reinforcement learning (RL) enables adaptive and autonomous decision-making in embedded, edge, and heterogeneous computing systems. Field-programmable gate arrays (FPGAs) and integrated circuits (ICs)...
The article titled "What's in the Box? Distinguishing Acceptable Traces from Unacceptable Ones" discusses how to transform scattered requirements into deployable agents. It focuses on identifying which traces are acceptable and which are not for effective deployment. The piece was originally published on Towards Data Science.
Camera design heavily influences perception task performance, yet cameras are typically designed by domain experts through costly experimentation, in isolation from the tasks they serve. Existing join...
A single observation can admit several plausible futures, making uncertainty an essential part of world modelling. However, quantum generative models remain underexplored for this task. We introduce Q...
Vision-language models (VLMs) are exact on small sets and drift into estimation on larger ones, a profile reminiscent of children before they master counting. Children cross the barrier with epistemic...
Large language models (LLMs) are increasingly used as judgment assistants and as stand-in participants in psychology experiments, yet little is known about how much their probability estimates move in...
Terminal X’s Eval Agent evaluates GPT‑6.1’s outputs using a 54‑criterion rubric, achieving an 88.6% match with senior investor judgment. The system detects 25% more deviations from a fund’s mandate compared to previous methods.
Long-horizon human-object-scene interaction (HOSI) is central to embodied AI, animation, and game development. Existing human-object interaction (HOI) and human-scene interaction (HSI) models excel in...
Simulation-ready world reconstruction demands physical interactivity beyond visual realism, which existing black-box 3D generation fails to deliver. We present NeoWorld-3, a coding-agent framework tha...