AI Paper Atlas

Research map / Learning theory and algorithms / Combinatorial and search optimization

Classical and HTN planning

Designs heuristics, compilations and symbolic search for numeric and hierarchical planning.

145 accepted papers at ICML, NeurIPS, ICLR, CVPR and AAAI (2016–2026) · an approach in Combinatorial and search optimization, keyword cluster “planning · search algorithm · tree search”

State History Tried Preprints Who Export

Where it stands

Not enough benchmark data Fewer than four papers report the same benchmark, so there is no record to follow.

33 papers in 2023–24 and 24 in 2025–26 (at ICML, NeurIPS, ICLR, CVPR and AAAI); its share of the topic shrank, from 9.5% to 6.6%.

How this is decided

A benchmark is tracked when at least four papers of this approach report their own method on the same dataset and metric in at least two different years. Its record is the best number reported up to 2024 compared with the best reported in 2025–26: still improving means at least 1% better, flat means at most 0.2% better with at least two papers from 2025–26 trying. Numbers on a different scale from the rest (a fraction among percentages) and far outliers are left out. Results come from different papers with different setups, so they are signals, not head-to-head comparisons. The share of papers is counted at ICML, NeurIPS, ICLR, CVPR and AAAI.

How it got here

2016: 7162017: 10172018: 9182019: 18192020: 19202021: 12212022: 13222023: 15232024: 18242025: 9252026: 1526

Most cited paper of each year

Earliest papers here

What has been tried

117 papers here report 953 measured changes (a component added, removed or swapped, compared with a baseline): helped 61%, no clear effect 8%, hurt 22%, mixed 8%. Papers mostly publish changes that helped, so "helped" is over-represented.

Ablations in recent papers

What was changedMeasured onResultEffectPaper
remove the optimization-before-first-plan improvementIPC-14 and benchmark set · coverage (optimally solved instances)147 -> 145HurtAbstract Action Scheduling for Optimal Temporal Planning via OMT (AAAI 2024 · 6 citations)
Reduce the number of feasibility and buyability samples25-molecule subsample · SSPHurtRetro-fallback: retrosynthetic planning in an uncertain world (ICLR 2024 · 4 citations)
Add synthetic distance D to Retro* guidanceUSPTO-190, N=500 · solve rate (%)35.8 -> 37.4HelpedDouble-Ended Synthesis Planning with Goal-Constrained Bidirectional Search (NeurIPS 2024 · 3 citations)
Add achiever-based optimization to the basic NTCORE compilationAll domains (512 instances) · coverage289 -> 351; 21.4%HelpedDealing with Numeric and Metric Time Constraints in PDDL3 via Compilation to Numeric Planning (AAAI 2024 · 2 citations)
Use numeric variables in iPDB patterns rather than ignoring all numeric variablesNumeric planning benchmarks · state expansionsHelpedPDBs Go Numeric: Pattern-Database Heuristics for Simple Numeric Planning (AAAI 2025 · 1 citation)
add sub-goal decomposition to System-1.5Maze Navigation · plan validity50.0 -> 70.4HelpedSystem 1.x: Learning to Balance Fast and Slow Planning with Language Models (ICLR 2025 · 1 citation)
Improve the dependency graphHard-to-ground domains · coverage262 -> 212HurtOptimizing the Optimization of Planning Domains by Automatic Action Schema Splitting (AAAI 2024 · 1 citation)
Replace the k-medians-with-penalties subroutine with k-mediansAnt U-Maze and Fetch-Reach · average planning timeHurtDiscovering Options That Minimize Average Planning Time (AAAI 2025 · 0 citations)
Replace the original captime-doubling condition with the refined conditionLog-Laplace utility; other utility functions show similar improvement · optimality guarantee and time per configurationHelpedUtilitarian Algorithm Configuration for Infinite Parameter Spaces (ICLR 2025 · 0 citations)
Remove the location-x-y-is-visited variablesVisit-All · river measure1 to 2HurtNovelty vs. Potential Heuristics: A Comparison of Hardness Measures for Satisficing Planning (AAAI 2024 · 0 citations)
Vary the mirror descent stepsize7-card 4-hint Hanabi · expected returnMixedThe Update-Equivalence Framework for Decision-Time Planning (ICLR 2024 · 0 citations)
add stochastic additional planning steps during fine-tuningAssociative Recall, larger inputs · accuracyHelpedDNCs Require More Planning Steps (ICML 2024 · 0 citations)

Recent preprints

Loading recent arXiv preprints…

    Who publishes on it

    Institutions on the most papers of this approach since 2023 (of 57 papers; from OpenAlex and the papers' affiliations).

    Use it

    Download BibTeX of 40 key papersOpen the topic in the interactive map

    Get alerts. Describe your idea in scime atlas and save it (free scime account): you get a weekly email when new preprints land close to it.

    Same keyword cluster

    Elsewhere in the topic

    Benchmark numbers, ablations and baseline numbers are extracted by AI from each paper's full text and can be wrong; the paper is the authority. Data: results index of 2026-11-02, citation counts from OpenAlex (2026-10-09).

    Get the next scime Dispatch and a monthly field update

    Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy