arXiv AI
Agent-G$^2$: Gaussian Guidance for Agentic Reinforcement Learning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 16
KnowGPO: Knowledge-Grouped Policy Optimization for Search Agents
KnowGPO introduces a reinforcement learning framework that groups search agent trajectories by the task-relevant knowledge they acquire, rather than by surface observations. By decomposing required information into atomic knowledge conditions and using the incremental knowledge gain as a process reward, KnowGPO provides finer-grained credit assignment for deep search tasks. Experiments on Xbench, BrowseComp-ZH, and GAIA demonstrate that KnowGPO outperforms outcome-only and process-supervision baselines by 3.8 to 4.2 points, with an 8B model rivaling or exceeding most 32B open-source systems.
arXiv AI
Aug 3
PAIR: Prefix-Aware Internal Reward Model for Multi-Turn Agent Optimization
arXiv:2605. 17877v2 Announce Type: replace Abstract: A significant hurdle for current LLMs is the execution of complex, multi-stage tasks.
arXiv AI
Oct 2
T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning
arXiv:2610.00388v1 Announce Type: cross Abstract: Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However,...
arXiv AI
Aug 25
EDGE: Experience-Distillation for Guided Exploration in Agentic Reinforcement Learning
arXiv:2608.21946v1 Announce Type: cross Abstract: Reinforcement learning with outcome-based objectives such as GRPO enables LLM-based agents to solve complex, long-horizon tasks, yet the reusable exp...
arXiv AI
Oct 15
Can an Agent Learn to Predict Its Own Failure? Outcome-Grounded Confidence Calibration in LLM Agents
arXiv:2610.18614v1 Announce Type: new Abstract: Controlling an acting LLM agent means deciding, at each step of a long-horizon task, whether to trust its next action, abstain, or hand off to a human....
arXiv Machine Learning
Oct 23
MOER: Mix-Policy Optimization under Expert Prefix Guidance with Selective Rollback
MOER is a mix‑policy optimization framework that blends expert guidance with self‑exploration in reinforcement learning. It injects a decaying expert chain‑of‑thought prefix into prompts, progressively annealing the prefix length to encourage exploration, and uses a selective rollback mechanism to replace failed completions with the full expert trace, ensuring correctness. The method employs a harmonized mix‑policy objective that optimizes on‑policy tokens with a GRPO loss while supervising both expert prefix and completion tokens with a trust‑region SFT loss, leading to stable training and superior performance on mathematical and general reasoning tasks.