Topic
planning
Supply Chain AI shifts from planning to execution as manufacturers confront tariff uncertainty
As tariffs and trade disruptions escalate, manufacturers are turning to AI-powered supply chain orchestration to evaluate sourcing decisions before disruptions ripple through their networks. Kinaxis' Maestro platform helps companies model multiple scenarios simultaneously, enabling faster and more informed decision-making.
Business Gen Z Losing Faith in State Pension: UK Retirement Crisis Looms for Under-30s
A growing number of Gen Z workers in the UK, such as 20-something engineer Joel, are planning their finances without expecting to receive a state pension. With the state pension age rising to 68 and projections showing 17 million pensioners by 2070, experts warn this distrust could lead to risky investments or disengagement from saving. The triple lock mechanism is under fire from think tanks like the Resolution Foundation.
VOiLA Framework Uses Diffusion Models to Cut Sampling Cost by Three Orders for POMDP Planning
Researchers present VOiLA, a framework that learns POMDP models for online planning under uncertainty using conditional diffusion models. The approach reduces sampling cost by nearly three orders of magnitude, matches or exceeds Recurrent Soft Actor Critic with less than 10% of training data, and generalizes better to unseen environments. Real-robot tests achieved 10/10 task success using models trained solely on simulation.
Hierarchical Control in Multi-Agent Games: LLM Planning with RL Execution Outperforms Flat Learning
Researchers propose a hierarchical architecture where a large language model (LLM) acts as a centralized strategic controller selecting among specialized RL skill policies for a team of agents. In a 2v2 King of the Hill environment, the LLM+RL system achieved a 46.4% win rate, statistically equivalent to hand-crafted behavior trees (51.5%), and significantly outperformed flat RL. A user study found 60% of participants perceived the LLM+RL agents as the most human-like.
LLM-WikiRace Benchmark Reveals Frontier AI Models Still Struggle with Planning Over Knowledge Graphs
Researchers introduced LLM-WikiRace, a benchmark to evaluate large language models on planning, reasoning, and world knowledge using Wikipedia hyperlinks. Top models like Gemini-3, GPT-5, and Claude Opus 4.5 achieve superhuman performance on easy tasks but drop sharply on hard difficulty, with Gemini-3 succeeding in only 23% of hard games. The study reveals that world knowledge helps only up to a point; beyond that, planning and long-horizon reasoning are the limiting factors.
HOLO-MPPI Framework Promises Robust Motion Planning for Autonomous Robots Without Per-Scenario Tuning
HOLO-MPPI is a new motion planning framework that combines hierarchical policy learning with stochastic optimal control. It addresses the brittleness of end-to-end reinforcement learning and the scalability issues of manually designed priors for MPPI. Tested in autonomous driving scenarios, it outperforms baselines while maintaining real-time control.
Tensor-Coord: Algebraic Decomposition Enables Conflict-Free Multi-Agent LLM Planning
A new research paper introduces Tensor-Coord, a multilinear algebra framework that represents joint plans of multiple LLM agents as a third-order tensor. By decomposing the tensor, it identifies coordination conflicts and enables iterative replanning, achieving 100% conflict-free plans for 2-agent tasks and 80% for 3-agent tasks in simulated delivery scenarios.
PACT Hybrid Architecture Combines Small Language Model Planning with Reinforcement Learning for Enhanced Decision-Making
Researchers propose Plan, Align, Commit, Think (PACT), a hybrid architecture that couples a fast reactive reinforcement learning policy with a slow deliberative small language model (SLM) planner. The SLM asynchronously generates and validates action plans, which are executed directly once verified as safe through simulation. Evaluated on three FrozenLake configurations, PACT outperformed all baselines using a 2B-parameter SLM backbone, demonstrating that deliberative planning and reactive execution complement each other.
Business India's Irrigation Water Demand to Hit 807 BCM by 2050
India's irrigation water demand is projected to reach 807 billion cubic metres by 2050, according to the Ministry of Jal Shakti. The ministry advocates for water budgeting to manage resources effectively amid increasing agricultural and livestock demands.