Integrating locomotion and manipulation is essential for robot autonomy, but scaling standard Reinforcement Learning (RL) to complex tasks is severely bottlenecked by the slow, manual process of dense reward shaping. To bypass this limitation, we leverage Sample-based Model Predictive Control (SMPC) entirely in simulation as an automated, rapidly tunable expert to generate massive offline datasets.
We construct OEIS Open, a benchmark based on 492 open mathematical conjectures from the OEIS, formalized in Lean by Tsoukalas et al. Whereas these conjectures had previously been attempted only with a bespoke agent, our open-source evaluation code runs any generic language model (LM) against them, and is secure against LM cheating attempts.
Turning a research idea into a complete paper requires more than text generation: the system must retrieve literature, design and execute experiments, revise claims according to evidence, produce publication-ready figures, and maintain consistency across a long generation process. We present Spark-to-Paper, an end-to-end research paper generation system implemented as thirteen composable skills inside an existing coding assistant, without requiring a separate agent platform or orchestration service.
Agent skills are the de facto mechanism for extending LLM agents with reusable guidance. A skill can shape the agent's task execution, including planning, tool use, problem-solving, and validation.
Gist-based context compression---summarising older conversation history into compact representations---is a common approach in long-horizon language model agents, yet its effect on different types of memory retrieval is poorly understood. We use Salience-Weighted Consolidation (SWC), a biologically-inspired compression framework motivated by sleep-based memory consolidation, as a diagnostic probe to study when gist compression helps and when it hurts.
Self-correction is particularly useful when a failure constrains the next repair. Coding agents benefit from this property because compilers, tests, and execution traces turn many failures into typed recovery signals, but broad language-agent tasks often expose only a coarse task failure.
Autonomous logistics sorting systems (ALSS) are an important industrial application of embodied AI, which requires joint planning over spatially disjoint camera views. We formulate this setting as Joint Multi-Scene Understanding (JMSU).
OpenAI research reveals how enterprises are adopting agentic AI, using ChatGPT and Codex, and how frontier firms are pulling ahead in AI adoption.
AI agents are increasingly deployed for professional investment research, yet no benchmark captures the complexity of the full investor workflow. Existing benchmarks mainly target financial data extraction, a narrow slice that current models have largely saturated, while reference-based metrics and generic LLM-as-a-judge scoring fall short on the open-ended, long-form answers that real analyst queries demand.
Motion-centric video reasoning is fundamental to interactive applications such as robotic manipulation and autonomous navigation. However, multimodal large language models (MLLMs) typically process videos through sparse uniform sampling to control visual-token and attention costs.
Despite the wide deployment of memory in large-model agents, there is no unified formal account of what a memory is or when it is optimal. This paper takes a first step toward this account.
Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and reach decisions. As LLMs increasingly debate, advise, and think collaboratively with humans and each other, resistance to harmful persuasion becomes a core requirement for reliable behavior.
arXiv:2511. 19436v2 Announce Type: replace-cross Abstract: Existing Video Detailed Captioning (VDC) methods predominantly rely on costly human annotations or distillation from powerful proprietary models, creating a dependency on external supervision.
By Qiang Wang, Xinyuan Gao, Yuhang He, Jizhou Han, Jiangyang Li, SongLin Dong, Zhiheng Ma, Yihong Gong
arXiv:2608. 09959v1 Announce Type: cross Abstract: AI weather models are in the process of revolutionising weather forecasting.
By Anna Allen, Wessel P. Bruinsma, Michael Maier-Gerber, Harrison Cook, Matthew Chantry, Richard E. Turner
arXiv:2608. 10366v1 Announce Type: new Abstract: Real-world data science involves long-horizon workflows that span data wrangling, exploration, modeling, visualization, and validation, and require coordinated use of tools such as notebooks, IDEs, terminals, browsers, and databases within real operating environments.
By Mizanur Rahman, Mohammed Saidul Islam, Ridwan Mahbub, Md Tahmid Rahman Laskar, Shafiq Joty, Enamul Hoque Prince
arXiv:2608. 11095v1 Announce Type: new Abstract: Agentic coding READMEs like CLAUDE.
By Kushal Chakrabarti
arXiv:2608. 09934v1 Announce Type: cross Abstract: Large language model (LLM) agents improve task performance by decomposing problems into role-specialized behaviors.
By Vitalii Belov, Artyom Sosedka, Andrey Sakhovskiy, Elizaveta Kovtun, Artyom Boyarskikh, Semen Budennyy
arXiv:2509. 05624v3 Announce Type: replace-cross Abstract: How much information about an agent's underlying values can be recovered from its observable behavior?
By Jason Starace, Terence Soule
arXiv:2602. 24188v2 Announce Type: replace-cross Abstract: We present a scalable and verifiable methodology for evaluating language models in multi-turn interactions, using a suite of collaborative games that require effective communication about private information.
By Jacob Eisenstein, Fantine Huot, Adam Fisch, Jonathan Berant, Mirella Lapata
arXiv:2602. 02035v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact coordination effectiveness.
By Ahmad Farooq, Kamran Iqbal