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.

The paper proposes CoEvo-AHD, an LLM-driven co-evolutionary framework that co-evolves two coupled operator populations to design effective heuristics for combinatorial optimization problems with stron…

The paper introduces LinTree, a method that explicitly structures the search history of LLM reasoning traces using parent pointers, significantly improving task performance and search efficiency compa…

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.

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.

The paper introduces CHECKMATE, a novel framework that uses code evolution to automatically generate and optimize algorithms for complex combinatorial problems, outperforming state-of-the-art solvers.

The paper proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and rel…

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.

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

This paper introduces MCTS-Guided Group Relative Policy Optimization (M-GRPO) to enhance LLM spatial reasoning by improving the decomposition of complex tasks into optimal sub-tasks.

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 proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

The paper introduces DOMINO, a novel inductive framework that synthesizes domain-specific data for LLMs using only reference examples, significantly improving performance on challenging, implicitly de…

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…

EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

SCOPE introduces a data-free self-play framework that co-evolves a task-generating Challenger and a document-answering Solver, significantly improving open-ended performance on language models without…

This paper analyzes large-scale reasoning traces from LLM-based binary vulnerability analysis, identifying four structured, token-level implicit patterns that govern how LLMs explore code paths.

The paper proposes a hybrid reasoning framework where Large Language Models (LLMs) generate code to encode complex optimization problems into a preference-based Maximum Satisfiability (MaxSAT) format,…

The paper introduces Unified Context Evolution (UCE), a gradient-free framework that externalizes and manages agent experience into a typed, evolving library, significantly improving performance on mu…

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…