Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2606. 24976v1 Announce Type: cross Abstract: Foundation-model agents in multi-step, open-ended environments frequently suffer from compounding errors, where early mistakes contaminate long-horizon trajectories.
arXiv:2606. 26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale.
arXiv:2606. 26002v1 Announce Type: new Abstract: We present HiReLC, a hierarchical ensemble-reinforcement learning framework for automated joint quantization and structured pruning of deep neural networks.
arXiv:2606. 25964v1 Announce Type: cross Abstract: Small ($\sim$2B) GUI-grounding agents are attractive for on-device deployment, accessibility tooling, and low-cost iteration, but at this scale they face two open recipe questions: how to obtain bounding-box training data without expensive human annotation, and how to combine supervised fine-tuning with reinforcement learning.
arXiv:2606. 23195v2 Announce Type: replace Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherence.
arXiv:2605. 01708v3 Announce Type: replace-cross Abstract: Contemporary systems serving large language models (LLMs) have adopted prefill-decode disaggregation to load-balance between the compute-bound prefill phase and the memory-bound decode phase.
arXiv:2606. 25852v1 Announce Type: new Abstract: Group-based reinforcement learning effectively post-trains LLM agents for long-horizon, sparse-reward tasks by deriving step-level credit from trajectory outcomes.
arXiv:2606. 24980v1 Announce Type: new Abstract: Small language models offer an efficient alternative to large-scale systems, but their ability to execute structured algorithms over multiple dependent decisions remains poorly understood.
arXiv:2606. 25760v1 Announce Type: new Abstract: Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-severity ranking, and spatial safety regions.
arXiv:2606. 24937v1 Announce Type: cross Abstract: The Hitchhiker's Guide to Agentic AI is a comprehensive practitioner's reference for building autonomous AI systems.
A new system, known as Murakkab, optimizes the design and deployment of multistep workflows that power AI applications.
arXiv:2606. 25127v1 Announce Type: new Abstract: We investigate how reward design shapes the internal attention patterns of reinforcement learning agents trained for autonomous driving.
arXiv:2606. 25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.
arXiv:2606. 26027v1 Announce Type: cross Abstract: Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities.
arXiv:2606. 25170v1 Announce Type: cross Abstract: We study PAC learning in tabular discounted Markov decision processes with exogenous i.
arXiv:2606. 25122v1 Announce Type: cross Abstract: Autonomous aerial vehicles operating in shared airspace must predict the future positions of non-cooperative obstacles to plan evasive maneuvers before a collision becomes unavoidable.
arXiv:2606. 24965v1 Announce Type: cross Abstract: Reasoning about relational structures remains a significant challenge for neural models, particularly when they must systematically apply learned knowledge to problem instances that are harder than those seen in training.
arXiv:2606. 25526v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent.
arXiv:2606. 25394v1 Announce Type: new Abstract: Finding minimal arithmetic circuits for polynomials over finite fields is a combinatorially hard problem central to algebraic complexity theory.
arXiv:2606. 25532v1 Announce Type: cross Abstract: Artificial intelligence increasingly drives automated scientific discovery, yet contemporary generalist agents lack physical grounding, frequently hallucinating hardware-incompatible designs.