20 results for “Candidate-based planners”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Introduces Expand-and-Prune, a test-time framework that adapts candidate support and capacity for end-to-end driving planners.
This paper introduces the first LLM-generated, domain-independent heuristics for symbolic AI planning, using evolutionary search to surpass the performance of hand-engineered state-of-the-art methods.
This paper empirically demonstrates that the choice of plan representation (e.g., checklist vs. narrative) significantly impacts the robustness and success rate of LLM-based web agents.
The paper introduces a novel LLM-driven evolutionary framework to synthesize admissible, domain-specific pattern generators, enabling optimal classical planning with high performance and interpretabil…
The paper proposes an efficient inference procedure for generative planning models by modifying the Open-Closed List (OCL) search, achieving superior performance over existing baselines.
Zhiyuan Wen, Jiannong Cao, Peng Gao, Haochen Shi +3 more
The paper introduces MAP-PPL, a profile-conditioned multi-agent planning dataset, and PersonalPlan, a two-stage MAS planner that generates personalized and pedagogically scaffolded plans for programmi…
The paper introduces new benchmarks for complex asynchronous planning and demonstrates that general constraint satisfaction formalizers (like CP-SAT) significantly outperform direct LLM planning or tr…
The paper proposes a hybrid LLM-based assistance system that enhances traditional capability-based planning by providing natural language interaction, interpretability, and flexible knowledge model ad…
The paper introduces GONDOR, a memory-efficient extension of Greedy Best-First Search (GBFS) that enables search continuation under strict memory constraints by periodically compressing the search tre…
The paper proposes DecomposeR, a planner-centric framework that structures deep research into typed Directed Acyclic Graphs (DAGs) to explicitly improve the planning and execution of large language mo…
This paper introduces a controlled environment to study multi-turn long-horizon planning ability acquisition, shaping, and integration in foundation model agents.
The paper introduces a benchmark and framework to evaluate the generalization of world models in planning tasks.
Matteo Merler, Bowen Li, Josh Roy, Yichao Liang +3 more
This paper evaluates the effectiveness of coding agents in solving generalized task and motion planning problems.
Jalaj Bhandari, Dhawal Gupta, Hongli Zhan, Zhenting Wang +4 more
This paper evaluates a simple inference-time scaling approach for large language model agents on complex tasks.
The paper introduces a learned 'rerooter' mechanism to improve subgoal-based policy tree search, allowing scalable search in complex environments without the overhead of explicit subgoal generation.
The paper presents a constant-competitive algorithm for the Matroid Secretary Problem on graphic matroids using only an independence oracle.
This paper unifies the fragmented field of Tree-of-Thoughts (ToT) reasoning by mapping LLM-based search processes onto a formal taxonomy derived from classical heuristic search theory.
Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen +2 more
This paper introduces the PEEU method to improve the planning abilities of small multimodal web agents.