← Back to all news

AI agents

Tool use, function calling, orchestration and the protocols that let models act rather than only answer.

15,743 stories · RSS feed

arXiv Machine Learning
Oct 8

CM-DPO: Constraint-Margin Direct Preference Optimization for LLM Planning

CM-DPO introduces a Constraint-Margin Direct Preference Optimization method that replaces the binary preference signal of traditional DPO with a continuous margin based on a deterministic symbolic verifier, scaled by violation severity. Hard and soft constraints are separated via a lexicographic objective to prevent hard constraints from being traded off against preferences. Using procedurally generated constraint profiles and minimal-edit distillation within the SynPlan-R framework, an 8B model fine‑tuned with CM‑DPO achieves high pass and solve rates on several planning benchmarks, matching multi‑agent systems with lower latency and outperforming GPT‑4o on unseen tasks.

By Rabimba Karanjai, Qun Gu, Hemanth Hegadehalli Madhavarao, Wenhuan Sun, Xiaojiao Yu, Suryabhan Singh Hada, Libin N. George, Uma Kona, Richard Williamson, Linsey Pang, Prakhar Mehrotra
llmsagentsreinforcement-learningfine-tuningefficiencysafety
More like this →
arXiv Machine Learning
Oct 8

Ask the Expert: LLM-Guided Reinforcement Learning for Autonomous Cyber Defense

The paper introduces Ask the Expert, a training-time framework that leverages large language models (LLMs) to guide reinforcement learning for autonomous cyber defense. It summarizes complex cyber‑defense states, intermittently queries an LLM for host‑level defensive recommendations via a constrained action interface, and then uses those recommendations to shape rewards for PPO training. After training, the LLM is discarded, leaving a pure RL policy that improves sample efficiency and outperforms potential‑based reward shaping baselines on TTCP CAGE CC1 and CC2 scenarios.

By Fernando Martinez, Abhishek Satyam, Tao Li, Junaid Farooq, Ying Wang, Juntao Chen
llmsagentsreinforcement-learning
More like this →
arXiv Computer Vision
Oct 8

CADReasoner: Iterative Program Editing for CAD Reverse Engineering

CADReasoner is a model that iteratively refines its CAD reconstruction by comparing the input shape with the predicted mesh, outputting a runnable CadQuery Python program. It fuses multi‑view renders and point clouds and uses a scan‑simulation protocol to bridge realism gaps during training and evaluation. The approach achieves state‑of‑the‑art performance on DeepCAD, Fusion 360, and MCB benchmarks for both clean and scan‑sim tracks.

By Soslan Kabisov, Vsevolod Kirichuk, Andrey Volkov, Gennadii Savrasov, Marina Barannikov, Anton Konushin, Andrey Kuznetsov, Dmitrii Zhemchuzhnikov
agentsbenchmarks
More like this →
arXiv Machine Learning
Oct 8

How Fragile Is On-Device Language Model Safety? Localizing Safety-Critical Parameters for Sparse Fault Analysis

The paper examines the safety of small language models (SLMs) deployed on resource‑constrained, on‑device platforms, focusing on the LLaMA‑2‑7B‑Chat model. It shows that safety‑sensitive behavior is concentrated in a sparse subset of parameters, particularly the MLP down_proj layer, and that altering only 0.19% of these weights can significantly affect safety metrics while leaving overall accuracy largely unchanged. The study suggests that targeted fault analysis and selective integrity protection could improve safety for on‑device, agentic language models.

By Muhammad Zeeshan Karamat, Christiana Chamon Garcia
llmsagentsmultimodalsafety
More like this →
arXiv Machine Learning
Oct 8

RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments

arXiv:2610.10409v1 Announce Type: cross Abstract: General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities car...

By Zhiqin Yang, Chenxin Li, Xiaomeng Hu, Yibin Liu, Weidong Huang, Jiankai Sun, Haitao Li, Zijian Wu, Yuzhi Huang, Fanding Huang, Hanwen Sun, Jiashun Liu, Jingqi Tong, Mingxin Huang, Shaoli Hu, Shijue Huang, Tianyi Bai, Xinyuan Wang, Yunlong Lin, Zhengyang Tang, Zhexin Zhang, Zhuo Chen, Xierui Song, Juntao Dai, Boyuan Chen, Jiaming Ji, Fangneng Zhan, Mengkang Hu, Wei Xue, Yonggang Zhang, Han Hu, Tsung-Yi Ho, Yike Guo
agentscomputer-visionroboticsmultimodalbenchmarks
More like this →
arXiv Machine Learning
Oct 8

ExperienceIndex: Artifact-Grounded Memory

arXiv:2610.10091v1 Announce Type: cross Abstract: Knowledge-intensive tasks require answering many questions by reasoning about a shared corpus of artifacts (e.g., court cases, or scientific literatu...

By Peter Baile Chen, Geoffrey X. Yu, Xinming Liu, Samuel Madden, Dan Roth, Jacob Andreas, Doug Downey, Michael Cafarella
agentsdata-engineering
More like this →
arXiv Machine Learning
Oct 8

Multi-Agent Coordination via Support-Preserving Distillation

The paper introduces Mode‑Support Semi‑Discrete Optimal Transport (MoSDOT) to address a failure mode in offline multi‑agent reinforcement learning where flow‑based teachers produce conflicting coordination modes. MoSDOT aggregates multimodal replay into a finite mode support with specified capacities and assigns each noise sample to a single mode before teacher training, thereby preventing the teacher from generating samples between valid modes. Experiments on controlled diagnostics and offline MARL benchmarks show that MoSDOT improves endpoint quality and routing consistency, especially on datasets with multimodal joint behavior.

By Sangmin Lee, Youngju Na, Chanmi Lee, Sung-eui Yoon
agentsefficiencymultimodalbenchmarks
More like this →