ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Ranking
Overall
82
Content
95
Popularity
N/A
No observed public metrics; popularity remains neutral/archived.
Merged summary
TL;DR - ProCredit improves reinforcement learning for long-horizon agents by rerunning acceptance checks after each tool-use turn and rewarding verified progress where it occurs. This provides denser, more precise credit than final outcome rewards alone.
- Measures each turn’s reward as the change in task progress, distinguishing productive actions from queries and near-successes from weaker failures.
- Assigns credit both across attempts for the same task and across turns within each trajectory.
- On AppWorld, it outperformed outcome- and progress-based baselines across three Qwen3.5 model scales and two test sets.
- At 4B parameters, it exceeded the strongest outcome-reward baseline by 4.1 percentage points; ablations attribute the gain to turn-level credit assignment rather than trajectory-level progress scoring.
Sources (1)
ProCredit: From Outcome Rewards to Progress Credit in Agentic Reinforcement Learning
Public signals
N/A
TL;DR - ProCredit improves reinforcement learning for long-horizon agents by rerunning acceptance checks after each tool-use turn and rewarding verified progress where it occurs. This provides denser, more precise credit than final outcome rewards alone.
- Measures each turn’s reward as the change in task progress, distinguishing productive actions from queries and near-successes from weaker failures.
- Assigns credit both across attempts for the same task and across turns within each trajectory.
- On AppWorld, it outperformed outcome- and progress-based baselines across three Qwen3.5 model scales and two test sets.
- At 4B parameters, it exceeded the strongest outcome-reward baseline by 4.1 percentage points; ablations attribute the gain to turn-level credit assignment rather than trajectory-level progress scoring.