Tool use, function calling, orchestration and the protocols that let models act rather than only answer.
arXiv:2606. 25012v1 Announce Type: new Abstract: Many reinforcement learning (RL) problems in the infinite-horizon average-reward setting require optimizing multiple conflicting objectives while satisfying multiple safety constraints.
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. 25335v1 Announce Type: new Abstract: Multi-Agent Reinforcement Learning (MARL) value factorization methods can suffer from a loss of plasticity, gradually failing to adapt when transferring to new task instances.
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. 25996v1 Announce Type: cross Abstract: We introduce Autodata, a general method that enables AI agents to act as data scientists who build high quality training and evaluation data.
arXiv:2505. 19532v2 Announce Type: replace Abstract: The current state-of-the-art backdoor attacks against Reinforcement Learning (RL) rely upon unrealistically permissive access models, that assume the attacker can read (or even write) the victim's policy parameters, observations, or rewards.
arXiv:2606. 25519v1 Announce Type: cross Abstract: Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-answer accuracy or per-token latency.
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. 26057v1 Announce Type: cross Abstract: AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems.
A new system, known as Murakkab, optimizes the design and deployment of multistep workflows that power AI applications.
arXiv:2606. 24899v1 Announce Type: new Abstract: AI-assisted mathematics is often evaluated on solving predefined problems.
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:2510. 17059v2 Announce Type: replace Abstract: Zero-shot imitation learning requires an agent to reproduce expert behavior from a single demonstration without additional environment interaction or gradient updates at test time.
arXiv:2603. 23129v4 Announce Type: replace Abstract: G\"odel agent realize recursive self-improvement: an agent inspects its own policy and traces and then modifies that policy in a tested loop.
arXiv:2602. 18266v2 Announce Type: replace Abstract: Automated methods for discovering mechanistic simulator models from observational data offer a promising path toward accelerating scientific progress.
arXiv:2606. 25556v1 Announce Type: cross Abstract: Stepwise group-based RL is an attractive way to train long-horizon LLM agents without a learned critic: it reuses multiple sampled rollouts to estimate local advantages.
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.
arXiv:2606. 25073v1 Announce Type: new Abstract: In cooperative multi-agent reinforcement learning (MARL), from a deployment perspective, it is challenging and expensive to train agents from scratch for each new environment or task.
arXiv:2606. 24958v1 Announce Type: new Abstract: Collective behavior arises when locally interacting units produce coordinated global organization, from synchronization in dynamical systems to task-relevant information flow on graphs.
arXiv:2606. 25115v1 Announce Type: new Abstract: On-device language-model agents improve by accumulating experience in retrieved memory rather than by updating weights.