Progress Advantage: Annotation-Free Step-Level Scoring for LLM Agents via RL Post-Training
Researchers introduce 'progress advantage,' a method that derives implicit step-level reward signals for LLM agents directly from the log-probability ratio between an RL-trained policy and its reference policy, without requiring dedicated process reward model training. The approach is shown to recover the optimal advantage function under a general stochastic MDP formulation, making it annotation-free and domain-agnostic. Validated across five benchmarks and four model families on tasks including test-time scaling, uncertainty quantification, and failure attribution, it outperforms confidence-based baselines and even dedicated trained reward models. The result is practically significant because building process reward models for agentic settings is currently a major bottleneck.
Related guides (3)
Related events (8)
RePro: Retrospective Progress-Aware Self-Refinement for LLM Agent Training
Researchers introduce RePro (Retrospective Progress-Aware Training), a framework addressing the gap between step-wise RL optimization and metacognitive task-progress awareness in LLM agents. The approach uses a forward-then-reflect rollout paradigm where agents execute actions online and then retrospectively assess step-wise progress given the completed trajectory and known outcome. Evaluated on WebShop, ALFWorld, and Sokoban, RePro achieves up to 12% absolute success rate gains over baseline Qwen-family models without requiring continuous external supervision.
APPO: Fine-grained branching and credit assignment for agentic RL in LLMs
Researchers introduce Agentic Procedural Policy Optimization (APPO), a reinforcement learning method that shifts branching and credit assignment from coarse tool-call boundaries to fine-grained decision points within generated sequences. APPO uses a Branching Score combining token uncertainty with policy-induced likelihood gains to select exploration points, plus procedure-level advantage scaling for credit distribution. Evaluated on 13 benchmarks, APPO improves strong agentic RL baselines by nearly 4 points while maintaining efficient tool use and interpretability. The work addresses a known weakness in multi-turn agentic RL: that influential decisions are distributed throughout sequences, not concentrated at tool-call boundaries.
ACPO: Adaptive Clip Policy Optimization improves RLVR training for LLM reasoning
A new arXiv preprint provides theoretical analysis of Reinforcement Learning from Verifiable Rewards (RLVR) updates, identifying off-policy degree and gradient expectation as key factors governing update dynamics. The authors show that differences in gradient steps per rollout substantially affect importance sampling ratio distributions and which tokens dominate updates. Based on this analysis, they propose Adaptive Clip Policy Optimization (ACPO), which adjusts clipping boundaries per token group by empirical variance of importance sampling ratios, outperforming DAPO and CISPO baselines on 3B and 7B models across math, tabular QA, and logic benchmarks.
ExpRL: RL-based mid-training using human QA data as reward scaffolds for LLM reasoning
ExpRL proposes an automated approach to LLM mid-training that replaces manually curated reasoning traces with large corpora of human-written QA data used as reward scaffolds rather than imitation targets. Reference solutions are hidden from the policy and used only to construct problem-specific grading rubrics, enabling dense process-level rewards that reinforce partial progress and intermediate reasoning steps. On challenging math reasoning benchmarks, ExpRL outperforms SFT, sparse-reward GRPO, and self-distillation as an RL initialization strategy, with additional mixed-domain experiments suggesting broader applicability.
STARE: Token-level advantage reweighting to prevent entropy collapse in GRPO-style RL training
Researchers introduce STARE, a method addressing policy entropy collapse in GRPO-style reinforcement learning from verifiable rewards (RLVR) for LLM post-training. Through first-order gradient analysis, they identify a token-level credit assignment mismatch and propose selectively reweighting advantages for entropy-critical tokens using batch-internal surprisal quantiles plus a closed-loop entropy gate. Evaluated across 1.5B–32B models on short/long chain-of-thought and multi-turn tool use tasks, STARE outperforms DAPO and other baselines by 4–8% on AIME24/25 while sustaining stable training over thousands of steps.
LamPO: Lambda-Style Policy Optimization with Pairwise Decomposed Advantage for Reasoning LMs
LamPO proposes a new RLVR training objective that replaces GRPO's scalar group-relative advantages with a Pairwise Decomposed Advantage, aggregating pairwise reward gaps within response groups and weighting comparisons by confidence-aware log-probability differences. The method retains a critic-free, clipped-update PPO-style structure and optionally adds a ROUGE-L-based dense auxiliary reward to reduce sparsity. Experiments on AIME24, AIME25, MATH-500, and GPQA-Diamond using Qwen3-1.7B, Qwen3-4B, and Phi-4-mini show consistent improvements over GRPO and other RLVR variants with more stable training dynamics.
Adaptive Data Scheduling (ADS) improves LLM reinforcement learning post-training by 5.2% over GRPO
Researchers propose Adaptive Data Scheduling (ADS), a dual-level framework that replaces uniform sampling in RL post-training with adaptive distribution over semantic clusters and policy-boundary sample selection. Evaluated across three LLMs and seven reasoning benchmarks, ADS improves average accuracy by 5.2% over GRPO and generalizes across RL objectives. The method addresses a structural limitation in standard RL post-training pipelines by accounting for semantic data structure and evolving policy capability during training.
Success Visitation Matching transforms sparse RL rewards into dense process rewards
A new arXiv paper proposes a method to convert sparse outcome rewards into dense process rewards by training a discriminator to distinguish successful from unsuccessful episodes and using it to guide policy learning toward the state-action visitations of successful trajectories. The approach is proven to preserve the optimal policy while providing denser feedback on task progress. Experiments focus on robotic manipulation finetuning in both simulated and real-world settings, showing faster RL convergence than sparse-reward baselines.