marine-vehicle-navigation-llm-asked-only-emit-ordered-macro-action CLM-0086For marine vehicle navigation, an LLM asked only to emit an ordered macro-action skeleton produces syntactically and topologically usable plans but cannot set physically feasible step durations; letting a differentiable physics surrogate optimize the durations turns plans that collide on every mission into collision-free ones, while wrong skeleton topology remains unrecoverable because the optimizer only rescales timings.
Capability: Turning plans into physical action
Observed on
6-DOF AUV and 3-DOF differential-drive ASV, five simulated offshore wind-farm missions per platform, one local ~26B model called once per mission, analytical Fossen simulator plus .
Sources
- Measured: ungrounded baseline reached 0% of goals with dozens of collisions on both platforms; grounded planners reached 100% with zero collisions in the analytical simulator and cut GazeboSim goal-distance error 70-82% (ASV) and ~93% (AUV). 200 planning trials per platform showed 200/200 and 197/200 valid skeletons, with 4 AUV cases of suboptimal topology silently absorbed by duration tuning. Single model, simulation only, no real-world trials.
Disagreeing is the most useful thing you can do here. Nothing on this page waits for a reviewer: the counts above move when evidence lands, and every source stays attached with who brought it.
Related claims
- For long-horizon embodied task planning where a symbolic model defines action preconditions and effects, correcting a violated plan by edits the action model itself implies (inserting the missing navigate or open) raises plan success more per LLM call than returning the violation to the LLM for replanning, and the gain persists for frontier models as well as compact ones.Planning a sequence of actions before acting · reviewed by AI
- For training-free MLLM-driven navigation (instruction-following and object-goal) in simulated indoor environments, gating each planner-proposed action on evidential support, geometric reachability and subgoal consistency before dispatch — and refusing a stop request unless semantic, geometric and progress checks all pass — raises success rate over letting the planner act directly, but the stop check buys completion at some cost in path efficiency.Turning plans into physical action · reviewed by AI
- For multi-step assembly task planning from an action history and a workstation image, prompting a multimodal LLM to emit a structured (JSON) state representation and propagate it through each predicted action — then truncating the plan at the predicted state closest to the inferred goal — raises action executability and lowers final-state error relative to predicting actions alone, at the cost of shorter plans (lower overlap with recorded human action sequences) and roughly eight times the latency.Planning a sequence of actions before acting · reviewed by AI
- For LLM agents on dependent multi-step tasks, success decays geometrically with the number of steps under a single per-step reliability parameter that rises with model scale but stays below 1, so long horizons eventually collapse even for the strongest deployed systems — and the decay tracks step count, not context length, since bounding the context window steepens the decay rather than easing it.Completing tasks that take many steps or many hours · reviewed by AI
- For LLM-driven robot manipulation where every tool call is schema-validated and every motion kinematically and collision-checked before execution, execution-time recovery mechanisms (retrying a failed plan with an alternative candidate, resetting to a collision-checked safe pose between stages) contribute more to end-to-end task success than canonical action sequencing, because most residual failures are transient planning or IK failures rather than wrong orderings.Turning plans into physical action · reviewed by AI
Notes
Drafted from the paper by a model and filed unreviewed. Visible here so it can be read, not because anyone has vouched for it: it does not move any technique's standing and does not count toward the internal scorecard. Drafted confidence: medium. Falsifier as drafted: An LLM that, given the same macro vocabulary, sets durations directly and reaches goals collision-free at rates matching the world-model optimizer; or a case where the duration optimizer repairs a wrong action topology. Proposed technique, not catalogued: World-model duration optimization over an LLM action skeleton.