FORGE: Form-Optimal Routing of Grounded Evidence for Frozen LLM Agents
cs.LG, cs.CL
Submitted: 2026-09-28
Updated: 2026-09-28
Comments: 34 pages. Project page: https://xixiaouab.github.io/projects/FORGE/
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- GPT-4 Technical Report
- Reasoning on a Budget: A Survey of Adaptive and Controllable Test-Time Compute in LLMs
- Lightweight Query Routing for Adaptive RAG: A Baseline Study on RAGRouter-Bench
- Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
- From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review
- Retrieval-Augmented Generation for Large Language Models: A Survey
- DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
- Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills
- ACON: Optimizing Context Compression for Long-horizon LLM Agents
- MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
- OpenAI o1 System Card
- Proximal Policy Optimization Algorithms
- DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
- Scaling LLM Test-Time Compute Optimally can be More Effective than Scaling Model Parameters
- PRIME: Training Free Proactive Reasoning via Iterative Memory Evolution for User-Centric Agent
- AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking in Large Language Models
- RAGRouter-Bench: A Dataset and Benchmark for Adaptive RAG Routing
- Corrective Retrieval Augmented Generation
- Don't Overthink It: A Survey of Efficient R1-style Large Reasoning Models
- Select-then-Solve: Paradigm Routing as Inference-Time Optimization for LLM Agents
Related papers
- Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
- AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
- Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
- Convergence issues in Relational Concept Analysis based on AOC-posets
- Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks