Draw2Think recasts geometric reasoning as agentic interaction with a constraint engine, achieving 95.9% predicate-level construction fidelity and up to 16.4% accuracy gains on solid geometry tasks.
hub Mixed citations
Tool-star: Empowering LLM-brained multi-tool reasoner via reinforcement learning
Mixed citation behavior. Most common role is background (50%).
15
Pith papers citing it
Background
50% of classified citations
hub tools
citation-role summary
background 5
baseline 1
dataset 1
other 1
citation-polarity summary
representative citing papers
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
ThinC trains small models to reason primarily in code rather than natural language, outperforming tool-integrated baselines and even larger models on competition math benchmarks.
COVERT generates verifiable synthetic tool-use environments for RL by validated trajectory synthesis and oracle-preserving augmentations, improving tool-use accuracy on BFCL v3 and ACEBench while remaining complementary to SFT.
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
PruneTIR prunes erroneous tool-call trajectories during LLM inference via three trigger-based components to raise Pass@1 accuracy and efficiency while shortening context.
TIDE-Bench is a new benchmark for tool-integrated reasoning that combines diverse tasks, multi-aspect metrics covering answer quality, process reliability, efficiency and cost, plus filtered challenging test sets.
Agent-World autonomously synthesizes verifiable real-world tasks and uses continuous self-evolution to train 8B and 14B agents that outperform proprietary models on 23 benchmarks.
MARL-Rad trains region-specific and global agents with reinforcement learning on clinical rewards to produce more accurate radiology reports than prior methods on MIMIC-CXR and IU X-ray datasets.
E3-TIR integrates expert prefixes, guided branches, and self-exploration via mix policy optimization to deliver 6% better tool-use performance with under 10% of the usual synthetic data and 1.46x ROI.
An empirical literature analysis reveals a bifurcation in RL environments into Semantic Prior (LLM-dominated) and Domain-Specific Generalization ecosystems with distinct cognitive fingerprints.
A comprehensive review of self-evolving AI agents that improve themselves over time, organized via a framework of inputs, agent system, environment, and optimizers, with domain-specific and safety discussions.
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.
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.
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
citing papers explorer
-
Learning Agentic Policy from Action Guidance
ActGuide-RL uses human action data as plan-style guidance in mixed-policy RL to overcome exploration barriers in LLM agents, matching SFT+RL performance on search benchmarks without cold-start training.
-
Teaching Language Models to Think in Code
ThinC trains small models to reason primarily in code rather than natural language, outperforming tool-integrated baselines and even larger models on competition math benchmarks.
-
ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents
ToolCUA introduces a trajectory scaling pipeline and staged RL to optimize GUI-tool switching, reaching 46.85% accuracy on OSWorld-MCP for a 66% relative gain over baseline.
-
Multi-Modal Multi-Agent Reinforcement Learning for Radiology Report Generation
MARL-Rad trains region-specific and global agents with reinforcement learning on clinical rewards to produce more accurate radiology reports than prior methods on MIMIC-CXR and IU X-ray datasets.
-
A Survey of Context Engineering for Large Language Models
The survey organizes Context Engineering into retrieval, processing, management, and integrated systems like RAG and multi-agent setups while identifying an asymmetry where LLMs handle complex inputs well but struggle with equally sophisticated long outputs.