AgentGym2: Benchmarking Large Language Model Agents in De-Idealized Real-World Environments (2026)
Most agent benchmarks test LLM agents under idealized conditions: tools are handed over ready-made, intermediate steps are skipped, and inputs are tidy and complete.
AgentV-RL: Scaling Reward Modeling with Agentic Verifier (2026)
Verifiers, or reward models, steer test-time scaling (TTS) in LLM reasoning, but they often fail on hard mathematical problems.
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training (2026)
Reward signals in LLM post-training are often noisy, sparse or ambiguous. When such errors pass through GAE, advantage estimates become distorted: credit drifts toward the end of a sequence (length hacking) or onto irrelevant tokens. Prior robust-RL work mostly cleans the reward model or filters data. This paper…

Co-authors here

12 of 17 co-authors with a page, the most papers together first.

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

Updated 2 November 2026