REVIEW 6 cited by
Learning adaptive planning representations with natural language guidance
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Effective planning in the real world requires not only world knowledge, but the ability to leverage that knowledge to build the right representation of the task at hand. Decades of hierarchical planning techniques have used domain-specific temporal action abstractions to support efficient and accurate planning, almost always relying on human priors and domain knowledge to decompose hard tasks into smaller subproblems appropriate for a goal or set of goals. This paper describes Ada (Action Domain Acquisition), a framework for automatically constructing task-specific planning representations using task-general background knowledge from language models (LMs). Starting with a general-purpose hierarchical planner and a low-level goal-conditioned policy, Ada interactively learns a library of planner-compatible high-level action abstractions and low-level controllers adapted to a particular domain of planning tasks. On two language-guided interactive planning benchmarks (Mini Minecraft and ALFRED Household Tasks), Ada strongly outperforms other approaches that use LMs for sequential decision-making, offering more accurate plans and better generalization to complex tasks.
Forward citations
Cited by 6 Pith papers
-
PartInstruct: Part-level Instruction Following for Fine-grained Robot Manipulation
PartInstruct is a new large-scale simulated benchmark with part-level language instructions and training demonstrations; current robot policies achieve at most 31.72% average success on it.
-
Hypothesis-driven Model Expansion under Uncertainty for Open-World Robot Planning
HUME lets robots generate, plan over, and actively verify object-centric hypotheses from foundation models so incomplete symbolic models become usable for open-world household tasks.
-
On the Limit of Language Models as Planning Formalizers
On simple planning domains, state-of-the-art LLMs can generate complete, solvable PDDL that often outperforms direct plan generation, but natural-language descriptions and complex domains sharply reduce accuracy.
-
Analogy making as amortised model construction
Analogy is formalized as a partial MDP homomorphism, and a library of reusable abstract modules is proposed to amortize the cost of constructing and solving internal models of novel situations.
-
WALL-E 2.0: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents
WALL-E 2.0 improves LLM agents by encoding learned environment rules as executable code that corrects an LLM world model, lifting ALFWorld success to 98%.
-
Large Language Models for Planning: A Comprehensive and Systematic Survey
A structured survey of LLM planning methods, benchmarks, and interpretability work, organized around a three-way taxonomy.
Discussion (0). Continue with ORCID to comment.