Latest papers from arXiv — updated daily across cs.AI, cs.LG, cs.CL, and cs.CV.
200 papers — updated daily from arXiv
Xinyuan Song, Zekun Cai
arXiv:2610.00010v1 Announce Type: new Abstract: Long-horizon language agents increasingly rely on external memory as a frozen world model, yet current memory systems are usually judged only by task success or token…
Xinyuan Song, Zekun Cai
arXiv:2610.00012v1 Announce Type: new Abstract: LLM agents increasingly act through modular systems, such as order, payment, inventory, and shipment services, where actions in one module change which transitions are…
Stefan G. Creadore
arXiv:2610.00015v1 Announce Type: new Abstract: Large-language-model agents can propose and execute actions, but proposal, authority, dispatch, verified external effect, and serving promotion are different claims. We…
Jiameng Zhang, Hongqiu Wu
arXiv:2610.00018v1 Announce Type: new Abstract: Role-specialized QA pipelines increasingly pass rationales from a reasoner to a verifier, but it is unclear what this message actually buys: better answers, stronger…
Jundong Hu, Shekar Ramachandran
arXiv:2610.00025v1 Announce Type: new Abstract: Agent harnesses increasingly want to run small language models (SLMs) on the microtasks around a frontier large language model (LLM) planner: auto-approving shell…
Khawaja Murad ul Hassan, Mehran Ebrahimi
arXiv:2610.00047v1 Announce Type: new Abstract: Diversity collapse in parallel chain-of-thought has motivated inference-time interventions built on a natural design: when a process reward model (PRM) prunes a chain,…
Ruoming Jin, Xinyu Li, Hao Zhou +6 more
arXiv:2610.00061v1 Announce Type: new Abstract: Personalizing large language models (LLMs) requires aligning generation behavior with user-specific preferences rather than aggregate quality. While Direct Preference…
Aubrey M. Brueckner, Darshil Patel, Yuhuan He +1 more
arXiv:2610.00074v1 Announce Type: new Abstract: K-Dense BYOK (bring your own keys) is a free, open-source AI research assistant for scientists in any field that runs on the researcher's own computer. The researcher…
Timothy Kassis
arXiv:2610.00084v1 Announce Type: new Abstract: Detailed profession-specific system prompts raise token use and estimated cost per response without a consistent accuracy gain. We evaluate Scientific Agents, an…
Sam Larson
arXiv:2610.00197v1 Announce Type: new Abstract: We investigate automated rewards for training language models in conversational humor, focusing on reward exploits and countermeasures. Two approaches aim to capture…
Yixi Zhou, Sikun Wang, Lei Fan +1 more
arXiv:2610.00212v1 Announce Type: new Abstract: Public-service recommendations require evidence that matches the requested service, scope, and date. Yet treating every missing detail as decisive can withhold useful…
Wooyoung Jung
arXiv:2610.00224v1 Announce Type: new Abstract: Building automation systems are increasingly represented as semantic knowledge graphs (KGs) using ontologies such as Brick and ASHRAE 223P, creating a machine-readable…