The paper introduces ORION, a hierarchical orchestrator that uses two LLM agents to translate service intents into structured requests and generate abstract placement plans for 6G network slices across multiple administrative domains. A cooperative multi‑agent RL coordinator then selects cross‑domain partitions, treating the plan as a persistent soft prior, while per‑domain agents place the functions. ORION’s key contribution is an outcome‑driven episodic memory that records network‑condition profiles, proposed plans, and verified feasibility outcomes, feeding this information back to the planner to improve admission rates by 4.6–11.5 percentage points over a planner without memory.
arXiv:2609.38108v1 Announce Type: new Abstract: Large language models (LLMs) enable agents to solve long-horizon tasks by generating a plan and then executing it in an environment. However, successfu...
arXiv:2606. 11440v1 Announce Type: new Abstract: Existing multi-agent LLM orchestration methods, ranging from brute-force ensembles to learned routers, select models and topologies based on task and model features.
FL-MAESTRO is a multi‑agent orchestrator that uses three specialized large language model agents to jointly decide the communication topology, per‑client resource allocation, and aggregation rule in each federated learning round. A coordinator merges the agents’ analyses, and a non‑LLM feasibility check validates the decision before execution. By filtering out clients whose updates would never be aggregated, the system eliminates the main source of wasted round energy in volatile edge networks and works across heterogeneous device classes without per‑class energy models, achieving comparable accuracy to the best energy‑aware baseline while reducing wasted energy from over a third to near zero on a non‑IID CIFAR‑10 benchmark.
Translating natural-language planning intent into verified plans is a longstanding challenge: people communicate goals in language, while classical planners require formal PDDL specifications. Recent agentic frameworks bridge this gap by orchestrating a pool of specialized repair agents inside a verifier-checked refinement loop, but the orchestrator at the centre is itself a prompted frontier LLM, paying a frontier-LLM API call at every refinement step.
DAGent introduces an Evaluate‑then‑Grow planning approach for deep research agents, building directed acyclic graphs incrementally based on confidence and uncertainty from completed tasks. The framework includes a hierarchical context layer for efficient query handling and a structural reinforcement learning component, DAGRPO, that rewards topology‑conditioned execution. Experiments on BrowseComp‑Plus, GAIA, and xbench‑DeepSearch show DAGent outperforming strong baselines across multiple backbones and scaling to large language models.
GADAR (Generalizing Across Domains via Action Ranking) is a learned policy for classical planning that accepts a domain description as input and constructs grounded actions in unseen domains without search. It uses a three‑layer architecture—lifted domain, binding, and chain layers—to embed domain structure, tie action applicability to lifted preconditions, and capture schema dependencies. In zero‑shot experiments across eight benchmark domains, a single GADAR model trained on seven domains solves 58.3% of test instances, matching closely the performance of domain‑specific models and outperforming random choice and a representation lacking the chain layer.
arXiv:2607.22465v3 Announce Type: replace Abstract: Modern enterprise agent deployments consist of a heterogeneous pool of large language models (LLMs) having diverse capabilities and cost. Existing...
arXiv:2608. 10714v1 Announce Type: cross Abstract: The Organic 6G vision of a network of networks spanning an edge-cloud continuum complemented by non-terrestrial resources requires, to realize its promise, service provisioning that is simple to operate, scalable across independently administered domains, and agile under domain churn (i.
arXiv:2509.26200v2 Announce Type: replace-cross Abstract: Agentic artificial intelligence is a candidate enabler of Level-4 autonomy in sixth-generation (6G) networks, but agents reasoning over a sha...
AgentServeSim is a simulation framework designed to model the execution of large language model (LLM) agent programs, capturing cross‑turn key‑value (KV) state retention, successor turn release, and scheduling decisions. Unlike existing simulators that operate on request streams, AgentServeSim treats the entire agent program as a single unit of execution, using a Program Control Block, Program Orchestrator, Retention Plane, and Dispatch Plane to emulate realistic serving dynamics. Validation against real vLLM deployments on two GPU platforms shows mean job completion time errors below 5.5%, and the simulator enables automated policy search that improves mean JCT by up to 2.8% over hand‑written policies. whyItMatters":"The simulator provides a realistic, CPU‑based tool for evaluating and optimizing LLM agent serving policies, achieving high fidelity to real deployments and enabling measurable performance gains."
arXiv:2608. 04265v1 Announce Type: cross Abstract: Evaluations of LLM planning agents largely ask whether a task succeeds or a declared plan is followed.
arXiv:2605.18859v3 Announce Type: replace-cross Abstract: LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single u...