WorkRover introduces recursive environment evolution and verifier-to-turn credit assignment to train long-horizon cowork agents, achieving significant improvements on five benchmarks.
ISBN 979-8- 89176-251-0
5 Pith papers cite this work, alongside 3 external citations. Polarity classification is still indexing.
5
Pith papers citing it
3
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 5roles
background 1polarities
unclear 1representative citing papers
AURA improves implicit-need coverage by 0.07 over ReAct baselines on a 100-query benchmark by inserting an intent inference step controlled by a gap score, while cutting probes 82% on factual tasks.
Agentic Monte Carlo enables RL-style optimization of black-box LLM agents by sampling from the optimal policy posterior using Sequential Monte Carlo.
citing papers explorer
-
WorkRover: Scaling Long-Horizon Cowork Agent Training Via Recursive Environment Evolution
WorkRover introduces recursive environment evolution and verifier-to-turn credit assignment to train long-horizon cowork agents, achieving significant improvements on five benchmarks.
-
AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents
AURA improves implicit-need coverage by 0.07 over ReAct baselines on a 100-query benchmark by inserting an intent inference step controlled by a gap score, while cutting probes 82% on factual tasks.
-
Agentic Monte Carlo: Simulating Reinforcement Learning for Black-Box Agents
Agentic Monte Carlo enables RL-style optimization of black-box LLM agents by sampling from the optimal policy posterior using Sequential Monte Carlo.
- $A^2E$ : An End-to-End Agent Auditing Engine
- Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift