SCRIBE introduces skill-conditioned rewards with intermediate behavioral evaluation to reduce noise in training tool-augmented agents, raising AIME25 accuracy from 43.3% to 63.3% on a Qwen3-4B model.
Reasoning through exploration: A reinforcement learning framework for robust function calling.arXiv preprint arXiv:2508.05118, 2025
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
EDAS modulates advantage signals in RLVR to penalize repeated errors more and rare errors less, yielding consistent gains on math benchmarks when added to existing methods.
ROSE is a system for cooperative elasticity that co-locates serving and rollout models on shared GPUs, delivering 1.3-3.3x higher end-to-end throughput than fixed-resource baselines while preserving serving SLOs.
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
A pipeline of dataset construction from prior work, AugFC parameter augmentation, and two-step LLM training improves function calling for financial APIs and is running in production.
citing papers explorer
-
SCRIBE: Structured Mid-Level Supervision for Tool-Using Language Models
SCRIBE introduces skill-conditioned rewards with intermediate behavioral evaluation to reduce noise in training tool-augmented agents, raising AIME25 accuracy from 43.3% to 63.3% on a Qwen3-4B model.
-
Leveraging Error Diversity in Group Rollouts for Reinforcement Learning
EDAS modulates advantage signals in RLVR to penalize repeated errors more and rare errors less, yielding consistent gains on math benchmarks when added to existing methods.
-
ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL
ROSE is a system for cooperative elasticity that co-locates serving and rollout models on shared GPUs, delivering 1.3-3.3x higher end-to-end throughput than fixed-resource baselines while preserving serving SLOs.
-
The Landscape of Agentic Reinforcement Learning for LLMs: A Survey
Survey that defines agentic RL for LLMs via POMDPs, introduces a taxonomy of planning/tool-use/memory/reasoning capabilities and domains, and compiles open environments from over 500 papers.
-
Data-Driven Function Calling Improvements in Large Language Model for Online Financial QA
A pipeline of dataset construction from prior work, AugFC parameter augmentation, and two-step LLM training improves function calling for financial APIs and is running in production.