Model Exploration And Search

via “graph search-based planning with hierarchical exploration”

Agent S: an open agentic framework that uses computers like a human

Unique: Implements classical graph search planning combined with LMM-based heuristics for node evaluation, enabling systematic exploration of action sequences with backtracking capabilities rather than greedy single-step decision making

vs others: Provides more systematic exploration than greedy agents through graph search, though at higher computational cost; enables recovery from dead-end paths through backtracking

via “interactive model exploration”

Interactive timeline of every major Large Language Model. Filterable by open/closed source, searchable, 54 organizations tracked.

Unique: The interactive exploration feature allows for dynamic filtering and searching, which is more engaging than static lists or documents.

vs others: Provides a more intuitive and user-friendly experience compared to traditional databases or spreadsheets.

via “automatic-search-strategy-selection-based-on-model-type”

Triton Model Analyzer is a tool to profile and analyze the runtime performance of one or more models on the Triton Inference Server

Unique: The Configuration System implements heuristics to automatically select search strategies based on parameter space size and model complexity, reducing user burden. This requires analyzing configuration metadata before profiling starts.

vs others: More user-friendly than manual strategy selection because it eliminates the need to understand optimization algorithms, whereas expert-oriented tools require users to choose strategies based on domain knowledge.

Explore and search fal models to find the right fit for your tasks. Generate content with any model and manage queued runs by checking status, fetching results, and cancelling when needed. Upload files and get shareable URLs for use in your runs.

Unique: Utilizes a centralized model registry with dynamic querying capabilities, enabling efficient searches across diverse model attributes.

vs others: More comprehensive than basic keyword searches in other model repositories due to its structured filtering options.

via “iterative-search-refinement-with-model-directed-queries”

Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks...

Unique: Implements a closed-loop search strategy where the model's reasoning directly controls search execution and evaluation, rather than treating search as a separate tool invoked once. The model maintains state across search iterations and makes explicit decisions about strategy pivoting, enabling adaptive research workflows.

vs others: More adaptive than static RAG systems that execute a single retrieval pass, and more transparent than black-box search ranking because the model's reasoning about search strategy is part of the output.

via “epsilon-greedy exploration with decaying exploration rate”

* 🏆 2015: [Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (Faster R-CNN)](https://papers.nips.cc/paper/2015/hash/14bfa6bb14875e45bba028a21ed38046-Abstract.html)

Unique: Applies the classic epsilon-greedy strategy from tabular RL to deep Q-learning with a decaying exploration rate, enabling a simple yet effective balance between exploration and exploitation without requiring explicit uncertainty estimation or intrinsic motivation mechanisms.

vs others: Simpler and more interpretable than curiosity-driven exploration or Thompson sampling, though less sample-efficient; enables convergence on Atari with minimal hyperparameter tuning compared to more sophisticated exploration strategies.

via “program-space search with llm-guided exploration”

### Audio Processing <a name="2023ap"></a>

Unique: Uses LLM as a learned heuristic within a structured search loop rather than as a one-shot generator, combining neural guidance with deterministic evaluation to explore discrete program spaces. Implements iterative refinement where the LLM learns from failed attempts through in-context examples, enabling discovery of solutions outside typical training data distributions.

vs others: Outperforms pure LLM code generation by grounding proposals in executable feedback, and outperforms traditional program synthesis by leveraging learned heuristics to prune the search space intelligently rather than relying on exhaustive enumeration or hand-crafted rules.

via “model-specific feature exploration”

via “rapid model exploration”