Image de couverture de livre

Tool-Schema Compression Enables Agentic RAG Under Constrained Context Budgets

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteur principal:	Sakizli, Furkan
Format:	Preprint
Publié:	2026
Sujets:	Software Engineering Artificial Intelligence Computation and Language I.2.7
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

TSCG: Deterministic Tool-Schema Compilation for Agentic LLM Deployments
par: Sakizli, Furkan
Publié: (2026)

Vibe Code Bench: Evaluating AI Models on End-to-End Web Application Development
par: Tran, Hung, et autres
Publié: (2026)

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones
par: Rai, Daking, et autres
Publié: (2025)

Automated Web Application Testing: End-to-End Test Case Generation with Large Language Models and Screen Transition Graphs
par: Le, Nguyen-Khang, et autres
Publié: (2025)

Narrow Transformer: StarCoder-Based Java-LM For Desktop
par: Rathinasamy, Kamalkumar, et autres
Publié: (2024)

Mechanistic Understanding of Language Models in Syntactic Code Completion
par: Miller, Samuel, et autres
Publié: (2025)

When Retrieval Hurts Code Completion: A Diagnostic Study of Stale Repository Context
par: Weng, Haojun, et autres
Publié: (2026)

Safety Under Scaffolding: How Evaluation Conditions Shape Measured Safety
par: Gringras, David
Publié: (2026)

A Language for Describing Agentic LLM Contexts
par: Pelc, Noga Peleg, et autres
Publié: (2026)

Plan with Code: Comparing approaches for robust NL to DSL generation
par: Bassamzadeh, Nastaran, et autres
Publié: (2024)

A Comparative Study of DSL Code Generation: Fine-Tuning vs. Optimized Retrieval Augmentation
par: Bassamzadeh, Nastaran, et autres
Publié: (2024)

A Framework for Testing and Adapting REST APIs as LLM Tools
par: Bandlamudi, Jayachandu, et autres
Publié: (2025)

Mind the GAP: Text Safety Does Not Transfer to Tool-Call Safety in LLM Agents
par: Cartagena, Arnold, et autres
Publié: (2026)

REPOT: Recoverable Program-of-Thought via Checkpoint Repair
par: Mazaheri, Parsa
Publié: (2026)

Learning Software Bug Reports: A Systematic Literature Review
par: Long, Guoming, et autres
Publié: (2025)

Improved IR-based Bug Localization with Intelligent Relevance Feedback
par: Samir, Asif Mohammed, et autres
Publié: (2025)

Simple and Effective Baselines for Code Summarisation Evaluation
par: Robinson, Jade, et autres
Publié: (2025)

AcTracer: Active Testing of Large Language Model via Multi-Stage Sampling
par: Huang, Yuheng, et autres
Publié: (2024)

Achieving Tool Calling Functionality in LLMs Using Only Prompt Engineering Without Fine-Tuning
par: He, Shengtao
Publié: (2024)

Finetuning LLMs for Automatic Form Interaction on Web-Browser in Selenium Testing Framework
par: Le, Nguyen-Khang, et autres
Publié: (2025)

Improving Existing Optimization Algorithms with LLMs
par: Sartori, Camilo Chacón, et autres
Publié: (2025)

Comparative Analysis of LLM Abliteration Methods: A Cross-Architecture Evaluation
par: Young, Richard J.
Publié: (2025)

Engineering A Large Language Model From Scratch
par: Oketunji, Abiodun Finbarrs
Publié: (2024)

LLM4PLC: Harnessing Large Language Models for Verifiable Programming of PLCs in Industrial Control Systems
par: Fakih, Mohamad, et autres
Publié: (2024)

AgentPulse: A Continuous Multi-Signal Framework for Evaluating AI Agents in Deployment
par: Gao, Yuxuan, et autres
Publié: (2026)

CIDR: A Large-Scale Industrial Source Code Dataset for Software Engineering Research
par: Savenkov, Vladislav
Publié: (2026)

ContractBench: Can LLM Agents Preserve Observation Contracts?
par: Wang, Jicheng, et autres
Publié: (2026)

Generative AI Toolkit -- a framework for increasing the quality of LLM-based applications over their whole life cycle
par: Kohl, Jens, et autres
Publié: (2024)

FREYR: A Framework for Recognizing and Executing Your Requests
par: Gallotta, Roberto, et autres
Publié: (2025)

Comprehensive Evaluation and Insights into the Use of Large Language Models in the Automation of Behavior-Driven Development Acceptance Test Formulation
par: Karpurapu, Shanthi, et autres
Publié: (2024)

CoTran: An LLM-based Code Translator using Reinforcement Learning with Feedback from Compiler and Symbolic Execution
par: Jana, Prithwish, et autres
Publié: (2023)

AgentAtlas: Beyond Outcome Leaderboards for LLM Agents
par: Mazaheri, Parsa, et autres
Publié: (2026)

Beyond Greenfield: The D3 Framework for AI-Driven Productivity in Brownfield Engineering
par: Sharma, Krishna Kumaar
Publié: (2025)

The Path Not Taken: Duality in Reasoning about Program Execution
par: Hasanov, Eshgin, et autres
Publié: (2026)

LLMORPH: Automated Metamorphic Testing of Large Language Models
par: Cho, Steven, et autres
Publié: (2026)

Natural Language Summarization Enables Multi-Repository Bug Localization by LLMs in Microservice Architectures
par: Oskooei, Amirkia Rafiei, et autres
Publié: (2025)

The Impact of Large Language Models on Open-source Innovation: Evidence from GitHub Copilot
par: Yeverechyahu, Doron, et autres
Publié: (2024)

GPT-4.1 Sets the Standard in Automated Experiment Design Using Novel Python Libraries
par: Fachada, Nuno, et autres
Publié: (2025)

Exploring LLMs for User Story Extraction from Mockups
par: Firmenich, Diego, et autres
Publié: (2026)

Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent
par: Xia, Bowei, et autres
Publié: (2026)