AINeutralarXiv – CS AI · May 117/10
🧠Researchers developed a method to extract and analyze search trees from LLM reasoning traces, revealing that large language models use shallower, more myopic planning strategies compared to humans. While LLMs generate extended chain-of-thought reasoning, their actual decision-making is driven primarily by shallow search rather than deep lookahead, contrasting sharply with human expert planning.
AIBullisharXiv – CS AI · May 117/10
🧠Researchers introduce the Context Gathering Decision Process (CGDP), a POMDP framework that formalizes how LLM agents should search and gather information from environments exceeding their context windows. The approach yields measurable improvements in multi-hop reasoning (up to 11.4%) and token efficiency (up to 39% savings) through explicit belief state management and programmatic exhaustion detection.
AINeutralarXiv – CS AI · Jun 236/10
🧠Researchers evaluated two Tree-of-Thought (ToT) search strategies for improving LLM reasoning and found that both methods have fundamental limitations under different computational constraints. DPTS struggles with low-budget scenarios due to cold-start bottlenecks, while SSDP depletes its search frontier through aggressive pruning, suggesting adaptive strategies are necessary for effective reasoning across varying resource levels.
🧠 Llama
AINeutralarXiv – CS AI · Jun 116/10
🧠TreeSeeker is a new inference-time framework that improves deep web search by using tree-structured trial-and-error navigation. The system balances exploration and exploitation through textual UCB signals, demonstrating consistent improvements over baseline models on multiple benchmarks.
AINeutralarXiv – CS AI · Jun 86/10
🧠Researchers introduce Front-to-Attractors (F2A), a new heuristic class that optimizes bidirectional search algorithms by replacing computationally expensive pairwise frontier evaluations with estimates to a small set of dynamically maintained attractor states. The approach achieves 11.2x reduction in pairwise evaluations while maintaining performance gains over simpler heuristics.
AINeutralarXiv – CS AI · Jun 56/10
🧠Researchers introduce OPT*, a scalable benchmark for training large language models to perform step-by-step optimization reasoning across expanding search spaces. The framework combines feasibility checkers with complexity parameters that scale task difficulty without requiring new human labels, enabling both solver-guided and offline reinforcement learning approaches to improve LLM reasoning capabilities.
AINeutralarXiv – CS AI · Jun 16/10
🧠Researchers introduce FML-Bench, a standardized benchmark for evaluating AI research agents that separates strategy from infrastructure, revealing that simple greedy algorithms perform comparably to complex tree-search methods. The study identifies that exploration strategy effectiveness depends on the underlying structure of optimization opportunities, with an adaptive agent demonstrating superior performance by switching strategies based on improvement stagnation detection.
AINeutralarXiv – CS AI · Apr 105/10
🧠Researchers have developed an interactive visualization system that displays the complete 181,440-state space of the 8-puzzle problem using GPU-based rendering, enabling students to explore search algorithm behavior in real-time. The system demonstrates that full state-space visualization is technically feasible and educationally valuable for AI education, bridging abstract algorithmic concepts with concrete puzzle manipulation.
AINeutralarXiv – CS AI · Mar 116/10
🧠Researchers developed Budget-Constrained Agentic Search (BCAS) to evaluate how search depth, retrieval strategies, and token budgets affect accuracy and cost in AI search systems. The study found that hybrid retrieval methods with lightweight re-ranking produce the largest gains, with accuracy improving up to a small cap of additional searches.
AIBullisharXiv – CS AI · Mar 36/109
🧠Researchers introduce MM-DeepResearch, a multimodal AI agent that combines visual and textual reasoning for complex research tasks. The system addresses key challenges in multimodal AI through novel training methods including hypergraph-based data generation and offline search engine optimization.
AINeutralarXiv – CS AI · Jun 24/10
🧠This paper evaluates simple baseline methods for immediate duplicate detection (IDD) in A* search algorithms using external memory storage like SSDs and HDDs. The research addresses a gap in literature by systematically studying IDD approaches and their interaction with OS-level caching mechanisms, providing foundational benchmarks for memory-intensive search problems.
AINeutralGoogle AI Blog · Mar 54/10
🧠The article discusses Google's AI Mode in Search and its query fan-out method for processing visual searches. It explains how AI technology understands and interprets visual search queries to provide relevant results.
