arXiv AI
AttnSR: Attention Step Reward for Long-Horizon Agentic RL
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv AI
Oct 15
DeltaTTG: Training Multi-Turn Agents with a Token-to-Go Progress Meter
arXiv:2610.17666v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) for multi-turn agents relies on sparse terminal rewards that say little about individual steps....
Hugging Face Trending Papers
Aug 17
TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approache...
arXiv Machine Learning
Sep 30
Where the Model Changes Its Mind: Hindsight-Divergence Localization for Efficient Reinforcement Learning with Verifiable Rewards
arXiv:2609.36864v1 Announce Type: new Abstract: Group-relative methods for reinforcement learning with verifiable rewards (RLVR) learn from differences in rollout outcomes. Independently sampling com...
arXiv AI
Aug 18
TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
arXiv:2608. 16156v1 Announce Type: new Abstract: Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult.
arXiv Machine Learning
Sep 24
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
arXiv:2609.27532v1 Announce Type: new Abstract: Long-horizon agentic tasks require an agent to modify an environment through a sequence of tool calls, with success determined by the final state. The...
arXiv Machine Learning
Jun 25
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
arXiv:2606. 26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreversible actions, and stochastic environment feedback make both human annotation and Monte Carlo estimation infeasible at scale.