arxiv arXiv cs.LG · 1h ago · research

Do Your Own Research: Learning to Forecast by Learning to Search

from English

Researchers introduce an agentic forecasting environment and dataset derived from over 2,100 resolved Polymarket questions to train language models to gather their own evidence. The system allows agents to acquire context via web search and financial time series at rollout time, constrained by leak filtering to ensure information precedes the question's cutoff.

Trained on Qwen3.5-35B-A3B using single-epoch GRPO with a Brier-score reward.
Calibration improves by 30-40% and search attempts decrease from 3.8 to 2.25 per rollout as evidence discipline is learned.
The model outperforms four frontier models, including Claude Opus 4.5 (soft-Brier 0.254 vs. 0.256), at approximately 5% of the inference cost.

The authors release the environment, dataset, and per-rollout records as a reusable harness for temporal forecasting agents.

Importance 2/3 New harness with differentiators arXiv cs.LG Alibaba (Qwen) AI agents Training methods

Read original

arxiv arXiv cs.CL · 8d ago · 8 views

VHD-Play generates agentic RL environments from solved mechanisms

VHD-Play is a pipeline that generates diverse agentic reinforcement learning environments by sampling and solving mathematical models before rendering their decision processes as stateful tools. This approach ensures that executable dynamics and trajectory-scoring references are inherited directly from the solved model, addressing the misalignment issues common in existing generation pipelines.

arxiv arXiv cs.CL · 8d ago · 10 views

SkillGym internalizes human skills into LLMs for real-world problem solving

Researchers introduce SkillGym, a framework that transforms human-written agent skills into executable, verifiable training environments for large language model agents. The system utilizes a skill-to-task pipeline to instantiate concrete tasks and verify outcomes with code-based checkers.

arxiv arXiv cs.CL · 23d ago · 34 views

ExecCritic uses role-specific RL to improve coding agents via test-guided repair

Researchers introduce ExecCritic, a framework that combines a test-verify-revise scaffold with role-specific reinforcement learning to enhance coding agents. The system separates test construction from source-code repair, using a Test agent to generate repository-native tests and a Repair agent to revise code based on execution feedback.

arxiv arXiv cs.AI · 106d ago · 13 views

Spotlight: Using Spot GPUs to Accelerate DiT RL Post-Training

Spotlight enables DiT RL post-training by leveraging idle spot GPUs, reducing costs by 1.4-6.4× while achieving superior image quality. It uses stale model weights in exploration and reconfigures sequence parallelism in real time, allowing efficient GPU utilization without breaking training pipelines.

arxiv arXiv cs.LG · 107d ago · 2 views

EnvRL: Leveraging Environment Dynamics in Agentic RL

EnvRL introduces a framework that enhances agentic reinforcement learning by incorporating environment dynamics through state prediction and inverse dynamics objectives. When trained with GRPO, EnvRL improves success rates of Qwen-2.5-1.5B-Instruct from 72.8% to 77.4% on ALFWorld and from 56.8% to 67.0% on WebShop.