ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.
hub Mixed citations
Spider: A large-scale human-labeled dataset for com- plex and cross-domain semantic parsing and text-to-sql task.arXiv preprint arXiv:1809.08887
Mixed citation behavior. Most common role is background (60%).
21
Pith papers citing it
Background
60% of classified citations
abstract
We present Spider, a large-scale, complex and cross-domain semantic parsing and text-to-SQL dataset annotated by 11 college students. It consists of 10,181 questions and 5,693 unique complex SQL queries on 200 databases with multiple tables, covering 138 different domains. We define a new complex and cross-domain semantic parsing and text-to-SQL task where different complex SQL queries and databases appear in train and test sets. In this way, the task requires the model to generalize well to both new SQL queries and new database schemas. Spider is distinct from most of the previous semantic parsing tasks because they all use a single database and the exact same programs in the train set and the test set. We experiment with various state-of-the-art models and the best model achieves only 12.4% exact matching accuracy on a database split setting. This shows that Spider presents a strong challenge for future research. Our dataset and task are publicly available at https://yale-lily.github.io/spider
hub tools
citation-role summary
background 3
dataset 2
citation-polarity summary
representative citing papers
DDS decomposes agentic data-system composition into bounded sub-searches via intent, operator DAG, per-system skills, and runtime attribution contracts, turning runtime failures into cited skill patches.
New Text-to-Big SQL metrics show that LLM agents must balance accuracy with cost and speed at scale, where GPT-4o trades some accuracy for up to 12x speedup and GPT-5.2 proves more cost-effective than Gemini 3 Pro on large inputs.
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and SQL-Spider.
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
TeCoD improves Text-to-SQL execution accuracy by up to 36% over in-context learning and cuts latency 2.2x on matched queries by extracting templates from historical pairs and enforcing them with constrained decoding.
Modular curriculum learning with tier-specific adapters outperforms standard fine-tuning on complex Text-to-SQL queries in Spider and BIRD benchmarks by avoiding catastrophic forgetting.
InCoder-32B-Thinking uses error-feedback synthesized thinking traces and a code world model to reach top open-source scores on general and industrial code benchmarks including 81.3% on LiveCodeBench and 84.0% on CAD-Coder.
LLMs drop 39% in performance during multi-turn conversations due to premature assumptions and inability to recover from early errors.
APPS benchmark shows models like GPT-Neo pass roughly 20% of test cases on introductory problems, indicating machine learning is beginning to learn basic coding.
MARS-SQL trains a multi-agent RL system with ReAct-style interaction and generative validation to produce SQL queries, reaching 77.84% execution accuracy on BIRD dev and 89.75% on Spider test.
XiYan-SQL achieves SOTA Text-to-SQL accuracy by combining schema filtering, a multi-generator ensemble fine-tuned on varied SQL formats, and a selection model.
CHESS deploys four LLM agents to retrieve information, prune schemas, generate refined SQL candidates, and validate via unit tests, reporting up to 71.10% accuracy on BIRD with 83% fewer calls than leading proprietary baselines.
RUBICON replaces opaque LLM-based tool orchestration in agentic AI with an explicit query algebra (AQL: Find, From, Where) executed via wrappers to deliver traceable, deterministic access to heterogeneous enterprise data systems.
Blue DIL is a new architecture that unifies structured enterprise data, LLM world knowledge, and personal context through declarative query plans and agents for multi-source multi-modal applications.
Phi-4-Mini achieves strong math and coding performance with only 3.8B parameters via high-quality synthetic data, while Phi-4-Multimodal uses Mixture-of-LoRAs to integrate modalities and top speech recognition leaderboards.
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.
Qwen2.5-Coder models claim state-of-the-art results on over 10 code benchmarks, outperforming larger models of similar size.
citing papers explorer
-
ExCyTIn-Bench: Evaluating LLM agents on Cyber Threat Investigation
ExCyTIn-Bench is the first benchmark of 7542 questions from Microsoft Sentinel threat investigation graphs, where the best LLM agent achieves a reward of 0.606.
-
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems
DDS decomposes agentic data-system composition into bounded sub-searches via intent, operator DAG, per-system skills, and runtime attribution contracts, turning runtime failures into cited skill patches.
-
Both Ends Count! Just How Good are LLM Agents at "Text-to-Big SQL"?
New Text-to-Big SQL metrics show that LLM agents must balance accuracy with cost and speed at scale, where GPT-4o trades some accuracy for up to 12x speedup and GPT-5.2 proves more cost-effective than Gemini 3 Pro on large inputs.
-
PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
PragLocker generates function-preserving but non-portable prompts for LLM agents via code-symbol semantic anchoring followed by target-model feedback noise injection.
-
Natural Language Interfaces for Spatial and Temporal Databases: A Comprehensive Overview of Methods, Taxonomy, and Future Directions
A literature survey that taxonomizes methods, datasets, and evaluation practices for natural language interfaces to geospatial and temporal databases while identifying recurring trends and future directions.
-
TreeCoder: Systematic Exploration and Optimisation of Decoding and Constraints for LLM Code Generation
TreeCoder improves LLM code generation accuracy by representing decoding as an optimizable tree search over programs with first-class constraints for syntax, style, and execution, outperforming baselines on MBPP and SQL-Spider.
-
LIMO: Less is More for Reasoning
LIMO achieves 63.3% on AIME24 and 95.6% on MATH500 via supervised fine-tuning on roughly 1% of the data used by prior models, supporting the claim that minimal strategic examples suffice when pre-training has already encoded domain knowledge.
-
Reliable Answers for Recurring Questions: Boosting Text-to-SQL Accuracy with Template Constrained Decoding
TeCoD improves Text-to-SQL execution accuracy by up to 36% over in-context learning and cuts latency 2.2x on matched queries by extracting templates from historical pairs and enforcing them with constrained decoding.
-
LeGo-Code: Can Modular Curriculum Learning Advance Complex Code Generation? Insights from Text-to-SQL
Modular curriculum learning with tier-specific adapters outperforms standard fine-tuning on complex Text-to-SQL queries in Spider and BIRD benchmarks by avoiding catastrophic forgetting.
-
InCoder-32B-Thinking: Industrial Code World Model for Thinking
InCoder-32B-Thinking uses error-feedback synthesized thinking traces and a code world model to reach top open-source scores on general and industrial code benchmarks including 81.3% on LiveCodeBench and 84.0% on CAD-Coder.
-
LLMs Get Lost In Multi-Turn Conversation
LLMs drop 39% in performance during multi-turn conversations due to premature assumptions and inability to recover from early errors.
-
Measuring Coding Challenge Competence With APPS
APPS benchmark shows models like GPT-Neo pass roughly 20% of test cases on introductory problems, indicating machine learning is beginning to learn basic coding.
-
MARS-SQL: A multi-agent reinforcement learning framework for Text-to-SQL
MARS-SQL trains a multi-agent RL system with ReAct-style interaction and generative validation to produce SQL queries, reaching 77.84% execution accuracy on BIRD dev and 89.75% on Spider test.
-
XiYan-SQL: A Novel Multi-Generator Framework For Text-to-SQL
XiYan-SQL achieves SOTA Text-to-SQL accuracy by combining schema filtering, a multi-generator ensemble fine-tuned on varied SQL formats, and a selection model.
-
CHESS: Contextual Harnessing for Efficient SQL Synthesis
CHESS deploys four LLM agents to retrieve information, prune schemas, generate refined SQL candidates, and validate via unit tests, reporting up to 71.10% accuracy on BIRD with 83% fewer calls than leading proprietary baselines.
-
An Alternate Agentic AI Architecture (It's About the Data)
RUBICON replaces opaque LLM-based tool orchestration in agentic AI with an explicit query algebra (AQL: Find, From, Where) executed via wrappers to deliver traceable, deterministic access to heterogeneous enterprise data systems.
-
Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications
Blue DIL is a new architecture that unifies structured enterprise data, LLM world knowledge, and personal context through declarative query plans and agents for multi-source multi-modal applications.
-
Phi-4-Mini Technical Report: Compact yet Powerful Multimodal Language Models via Mixture-of-LoRAs
Phi-4-Mini achieves strong math and coding performance with only 3.8B parameters via high-quality synthetic data, while Phi-4-Multimodal uses Mixture-of-LoRAs to integrate modalities and top speech recognition leaderboards.
-
StarCoder: may the source be with you!
StarCoderBase matches or beats OpenAI's code-cushman-001 on multi-language code benchmarks; the Python-fine-tuned StarCoder reaches 40% pass@1 on HumanEval while retaining other-language performance.
-
Supplement Generation Training for Enhancing Agentic Task Performance
SGT trains a lightweight model to generate task-specific supplemental text that improves performance of a larger frozen LLM on agentic tasks without modifying the large model.
-
Qwen2.5-Coder Technical Report
Qwen2.5-Coder models claim state-of-the-art results on over 10 code benchmarks, outperforming larger models of similar size.