Papers

Field

Top tools here

Open problems in Learning verifiable rewards

Poor credit assignment in diffusion model RL1 paper raises it · 1 addresses it
Limits efficiency and stability when fine-tuning diffusion models with black-box rewards.
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Modelsraises · addresses
Vanishing group-relative reward signals1 paper raises it · 1 addresses it
All rollouts receiving the same reward lose useful trajectory-level information for learning.
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresightraises · addresses
Memory inefficiency in LLM RL post-training1 paper raises it · 1 addresses it
High memory demands prevent scaling RL to larger models or longer training runs.
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketchesraises · addresses
Sparse terminal rewards break value tracking1 paper raises it · 1 addresses it
Standard critics fail to model value evolution along trajectories, harming credit assignment.
- TPPO: Tracking-Value PPO For Language Model Reasoningraises · addresses
Reward hacking in rubric-based RL1 paper raises it · 1 addresses it
Additive reward aggregation allows policies to exploit criteria compensation, degrading task performance.
- Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubricsraises · addresses

Named by an AI from these papers' abstracts.

Open problems

Recently funded

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable312 papers62 this week
optimal regret · near optimal · bandits209 papers38 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl171 papers32 this week
reinforcement learning rl · reinforcement learning · markov decision processes98 papers16 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable90 papers16 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Coming with more sources: repos

Activity

Recent papers

All in Research →

arXiv cs.CLOct 19
Where RL Breaks: Localizing and Repairing Failures via Targeted Continued Pretraining
Xinyi Wang, Danqi Chen
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve reasoning in language models, yet growing evidence suggests that it mostly sharpens what the base model can already do. This raises a practical question: when RL fails, what is the base model missing? We look inside the RL policy's own rollouts and find that failures are localized: whether a rollout fails is strongly predicted by a small set of characteristic n-grams, ranging from reflection phrases such as "let's recheck" to specific operations such as "the inverse of A". These failures persist throughout RL training, although they are not beyond the model's reach: other sampled answers to the same question are often correct. Building on this observation, we use the failure $n$-grams to retrieve text from the pretraining corpus and continue pretraining the base model on it before RL. The resulting corpus has only 35M tokens, 3--4 orders of magnitude smaller than typical mid-training. We evaluate this approach on OLMo2 and Qwen3 models trained with RL on (1) GSM8K; (2) a mixture of math, commonsense, and knowledge questions; and (3) general math and science reasoning. Despite its size, the corpus…
PDF arXiv
arXiv cs.LGOct 19
Is it RL or Data? A Controlled Comparison of GRPO and Rejection-Sampling Fine-Tuning
Lakshya Chaudhry
Bauer et al. (2026) showed that in low-data reinforcement learning with verifiable rewards, training GRPO on mixed-difficulty prompts gives up to 5x the sample efficiency of easy-only prompts. They did not test whether this benefit is specific to GRPO, or whether another post-training method given the same data would obtain it too. We test this on their procedural counting task with Qwen3-4B-Base and LoRA, comparing GRPO to rejection-sampling fine-tuning (RFT) on the same prompts, verifier and token cap. Six primary arms cross the two methods with three prompt sets (Easy, Mixed, and a Curated subset of prompts the base model sometimes solves, which makes GRPO's implicit filter explicit). We use three seeds per arm. Hypotheses and falsifiers were registered before training. To rule out a poorly tuned baseline, RFT receives a 27-run hyperparameter sweep, while GRPO uses Bauer et al.'s recipe unchanged. GRPO outperforms RFT at every prompt set: by 10.9 points on held-out test problems with curated prompts, and, in post hoc comparisons with matched rollout budgets, by 8.4 and 9.2 points on the easy and mixed prompts. On test the advantage survives the least favorable treatment of…
PDF arXiv
arXiv cs.LGOct 19
Detection Augmented Learning In Non-Stationary Bandit Environments
Argyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose, Venugopal V. Veeravalli
We study the problem of non-stationary bandits without knowledge of the environmental changes. We propose Detection Augmented Learning (DAL) a black-box paradigm that comprises three modular components: a bandit algorithm, a change detector, and a forced exploration schedule. This modular design enables its applicability across a broad spectrum of bandit problems, from classical to highly structured settings. First, we provide theoretical insights into DAL's strong empirical performance: a single regret bound shows that DAL transfers the regret of its stationary input to the piecewise stationary setting, attaining or improving the best known bounds in every setting considered. We further identify conditions under which DAL performs well in drifting environments. Then, we showcase DAL's practical performance and versatility through extensive experimentation in which DAL consistently surpasses all state-of-the-art methods, both prior-free and prior-based, across diverse non-stationary scenarios in nine bandit settings. Finally, we investigate the effectiveness of the forced exploration and show that a bandit-driven strategy improves performance and shortens detection delay.
PDF arXiv
arXiv cs.LGOct 19
Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines
Haoqun Cao, Yurun Yuan, Tengyang Xie
Reinforcement learning has become a central tool for large language model (LLM) post-training, where policy gradient methods are routinely deployed off-policy, even though vanilla policy gradient assumes on-policy sampling. We study when such off-policy deployment is justified, and what roles its core ingredients, including importance sampling, KL regularization, and baselines, play in handling the resulting distribution shift. We show that for a general class of off-policy policy gradient updates, consistency, in the sense that the optimal policy remains a stationary point, requires one of two structures at the optimal policy: trajectory-level importance weighting, which suffers from the well-known curse of horizon, or KL regularization with a baseline equal to the optimal soft value, instantiated by the grouped mean. Focusing on the KL route, we identify it with the group-relative policy gradient (GRPG) update, establish an equivalence to a trajectory-level Bellman residual minimization objective, and obtain a finite-sample regret bound under all-policy coverage. This also gives a theoretical account of a variant of the empirically successful GRPO objective. We further uncover…
PDF arXiv
arXiv cs.LGOct 19
Predictive Bandit Curriculum Reinforcement Learning via Gradient-Based Sample Group Discovery
Liang Xu, Shufan Shen, Zhongni Hou, Chao Bi, Yufei Zhang +3
Curriculum learning, which organizes training samples according to their learning priority, has been widely adopted in reinforcement learning to improve training efficiency. However, existing methods commonly construct curriculum units using predefined data properties and estimate their utility by simply aggregating a single proxy signal from recent training history.Such designs may group samples with different optimization effects and fail to anticipate how their utility evolves in relation to the policy. We propose Predictive Gradient-based Bandit (PGB) Curriculum, which first discovers optimization-aware learning units by clustering projected sample-level gradients. PGB then employs a lightweight temporal predictor to forecast the future utility of each unit and converts the predictions into a Boltzmann sampling distribution for adaptive data allocation. Experiments across multiple model scales and reasoning benchmarks show that PGB consistently outperforms standard GRPO, difficulty-based curricula, and history-based scheduling strategies, demonstrating improved data utilization and training efficiency.
PDF arXiv
arXiv cs.AIOct 19
The Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering
Hao Li, Minghui Ren, Shaowen Lu
The macroscopic capabilities of intelligent systems arise from the local interactions of many simple units. When such systems are deployed in the real world, their behaviour must nevertheless be constrained, leaving designers caught between releasing adaptability and preventing loss of control, yet without formal tools to resolve the dilemma. This paper proposes a unified research program for controlled emergence that restates this tension as a pair of dual problems: the forward problem explains macroscopic behaviour from local rules, and the inverse problem solves for controllable rules and readout mechanisms from a desired target. We take an augmented quintuple as the formal object shared by both ends, and decompose ``engineering'' into three independently measurable coordinates: controllability, reproducibility, and degree of formalizability. On this basis we give three testable working hypotheses (critical scale; the cooperation and trade-off between constraint and adaptability; minimal constraint) and one feasibility criterion, which reduce inverse design from unconstrained optimization to interval checking. The program takes explicit failure boundaries as its premise, does…
PDF arXiv

Papers

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable312 papers62 this week
optimal regret · near optimal · bandits209 papers38 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl171 papers32 this week
reinforcement learning rl · reinforcement learning · markov decision processes98 papers16 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable90 papers16 this week

Active contributors · 90 days

Activity · 12 weeks

Coming with more sources: repos

Recent papers

All in Research →

arXiv cs.CLOct 19
Where RL Breaks: Localizing and Repairing Failures via Targeted Continued Pretraining
Xinyi Wang, Danqi Chen
Reinforcement learning with verifiable rewards (RLVR) is widely used to improve reasoning in language models, yet growing evidence suggests that it mostly sharpens what the base model can already do. This raises a practical question: when RL fails, what is the base model missing? We look inside the RL policy's own rollouts and find that failures are localized: whether a rollout fails is strongly predicted by a small set of characteristic n-grams, ranging from reflection phrases such as "let's recheck" to specific operations such as "the inverse of A". These failures persist throughout RL training, although they are not beyond the model's reach: other sampled answers to the same question are often correct. Building on this observation, we use the failure $n$-grams to retrieve text from the pretraining corpus and continue pretraining the base model on it before RL. The resulting corpus has only 35M tokens, 3--4 orders of magnitude smaller than typical mid-training. We evaluate this approach on OLMo2 and Qwen3 models trained with RL on (1) GSM8K; (2) a mixture of math, commonsense, and knowledge questions; and (3) general math and science reasoning. Despite its size, the corpus…
PDF arXiv
arXiv cs.LGOct 19
Is it RL or Data? A Controlled Comparison of GRPO and Rejection-Sampling Fine-Tuning
Lakshya Chaudhry
Bauer et al. (2026) showed that in low-data reinforcement learning with verifiable rewards, training GRPO on mixed-difficulty prompts gives up to 5x the sample efficiency of easy-only prompts. They did not test whether this benefit is specific to GRPO, or whether another post-training method given the same data would obtain it too. We test this on their procedural counting task with Qwen3-4B-Base and LoRA, comparing GRPO to rejection-sampling fine-tuning (RFT) on the same prompts, verifier and token cap. Six primary arms cross the two methods with three prompt sets (Easy, Mixed, and a Curated subset of prompts the base model sometimes solves, which makes GRPO's implicit filter explicit). We use three seeds per arm. Hypotheses and falsifiers were registered before training. To rule out a poorly tuned baseline, RFT receives a 27-run hyperparameter sweep, while GRPO uses Bauer et al.'s recipe unchanged. GRPO outperforms RFT at every prompt set: by 10.9 points on held-out test problems with curated prompts, and, in post hoc comparisons with matched rollout budgets, by 8.4 and 9.2 points on the easy and mixed prompts. On test the advantage survives the least favorable treatment of…
PDF arXiv
arXiv cs.LGOct 19
Detection Augmented Learning In Non-Stationary Bandit Environments
Argyrios Gerogiannis, Yu-Han Huang, Subhonmesh Bose, Venugopal V. Veeravalli
We study the problem of non-stationary bandits without knowledge of the environmental changes. We propose Detection Augmented Learning (DAL) a black-box paradigm that comprises three modular components: a bandit algorithm, a change detector, and a forced exploration schedule. This modular design enables its applicability across a broad spectrum of bandit problems, from classical to highly structured settings. First, we provide theoretical insights into DAL's strong empirical performance: a single regret bound shows that DAL transfers the regret of its stationary input to the piecewise stationary setting, attaining or improving the best known bounds in every setting considered. We further identify conditions under which DAL performs well in drifting environments. Then, we showcase DAL's practical performance and versatility through extensive experimentation in which DAL consistently surpasses all state-of-the-art methods, both prior-free and prior-based, across diverse non-stationary scenarios in nine bandit settings. Finally, we investigate the effectiveness of the forced exploration and show that a bandit-driven strategy improves performance and shortens detection delay.
PDF arXiv
arXiv cs.LGOct 19
Anatomy of Off-Policy Policy Gradient: Importance Sampling, KL Regularization, and Baselines
Haoqun Cao, Yurun Yuan, Tengyang Xie
Reinforcement learning has become a central tool for large language model (LLM) post-training, where policy gradient methods are routinely deployed off-policy, even though vanilla policy gradient assumes on-policy sampling. We study when such off-policy deployment is justified, and what roles its core ingredients, including importance sampling, KL regularization, and baselines, play in handling the resulting distribution shift. We show that for a general class of off-policy policy gradient updates, consistency, in the sense that the optimal policy remains a stationary point, requires one of two structures at the optimal policy: trajectory-level importance weighting, which suffers from the well-known curse of horizon, or KL regularization with a baseline equal to the optimal soft value, instantiated by the grouped mean. Focusing on the KL route, we identify it with the group-relative policy gradient (GRPG) update, establish an equivalence to a trajectory-level Bellman residual minimization objective, and obtain a finite-sample regret bound under all-policy coverage. This also gives a theoretical account of a variant of the empirically successful GRPO objective. We further uncover…
PDF arXiv
arXiv cs.LGOct 19
Predictive Bandit Curriculum Reinforcement Learning via Gradient-Based Sample Group Discovery
Liang Xu, Shufan Shen, Zhongni Hou, Chao Bi, Yufei Zhang +3
Curriculum learning, which organizes training samples according to their learning priority, has been widely adopted in reinforcement learning to improve training efficiency. However, existing methods commonly construct curriculum units using predefined data properties and estimate their utility by simply aggregating a single proxy signal from recent training history.Such designs may group samples with different optimization effects and fail to anticipate how their utility evolves in relation to the policy. We propose Predictive Gradient-based Bandit (PGB) Curriculum, which first discovers optimization-aware learning units by clustering projected sample-level gradients. PGB then employs a lightweight temporal predictor to forecast the future utility of each unit and converts the predictions into a Boltzmann sampling distribution for adaptive data allocation. Experiments across multiple model scales and reasoning benchmarks show that PGB consistently outperforms standard GRPO, difficulty-based curricula, and history-based scheduling strategies, demonstrating improved data utilization and training efficiency.
PDF arXiv
arXiv cs.AIOct 19
The Forward/Inverse Duality of Controlled Emergence:A Computational Design Program from Explanation to Engineering
Hao Li, Minghui Ren, Shaowen Lu
The macroscopic capabilities of intelligent systems arise from the local interactions of many simple units. When such systems are deployed in the real world, their behaviour must nevertheless be constrained, leaving designers caught between releasing adaptability and preventing loss of control, yet without formal tools to resolve the dilemma. This paper proposes a unified research program for controlled emergence that restates this tension as a pair of dual problems: the forward problem explains macroscopic behaviour from local rules, and the inverse problem solves for controllable rules and readout mechanisms from a desired target. We take an augmented quintuple as the formal object shared by both ends, and decompose ``engineering'' into three independently measurable coordinates: controllability, reproducibility, and degree of formalizability. On this basis we give three testable working hypotheses (critical scale; the cooperation and trade-off between constraint and adaptability; minimal constraint) and one feasibility criterion, which reduce inverse design from unconstrained optimization to interval checking. The program takes explicit failure boundaries as its premise, does…
PDF arXiv

Open problems in Learning verifiable rewards

Poor credit assignment in diffusion model RL1 paper raises it · 1 addresses it
Limits efficiency and stability when fine-tuning diffusion models with black-box rewards.
- DiffusionART: Efficient, Stable and Scalable Reinforcement of Diffusion Modelsraises · addresses
Vanishing group-relative reward signals1 paper raises it · 1 addresses it
All rollouts receiving the same reward lose useful trajectory-level information for learning.
- Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresightraises · addresses
Memory inefficiency in LLM RL post-training1 paper raises it · 1 addresses it
High memory demands prevent scaling RL to larger models or longer training runs.
- LoGRA: Scaling LLM Reinforcement Learning with Low-Rank Gradient Sketchesraises · addresses
Sparse terminal rewards break value tracking1 paper raises it · 1 addresses it
Standard critics fail to model value evolution along trajectories, harming credit assignment.
- TPPO: Tracking-Value PPO For Language Model Reasoningraises · addresses
Reward hacking in rubric-based RL1 paper raises it · 1 addresses it
Additive reward aggregation allows policies to exploit criteria compensation, degrading task performance.
- Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubricsraises · addresses

Named by an AI from these papers' abstracts.

Fields · AI · updated 5m ago

Learning verifiable rewards

Found by the topic model: learning verifiable rewards, optimal regret, offline reinforcement learning.

164papers this week−17.6% vs last week

All papers · 880 With code · 27

Newest Most relevant

847 papers this month