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 verifiable336 papers38 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl190 papers30 this week
optimal regret · near optimal · bandits221 papers23 this week
reinforcement learning rl · reinforcement learning · markov decision processes108 papers15 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers12 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.AISep 27
The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration
Jin Cui, Xinyue Long, Boran Zhao, Pengju Ren, Hao Dong
Reinforcement learning with verifiable rewards (RLVR) is often limited by insufficient exploration: difficult problems can yield uniformly incorrect rollout groups and therefore little learning signal. We show that such failures need not reflect missing capability. Instead, finite sampling often concentrates on a problem-specific dominant reasoning strategy while leaving alternative strategies already supported by the model unexplored. Moreover, the accessibility of these strategies evolves during RL: some are internalized into autonomous behavior, while others become difficult to elicit before being absorbed. Motivated by these observations, we introduce Problem--Strategy Rollout Allocation (PSRA), which treats unguided and strategy-conditioned prompts as competing exploration arms and uses Bayesian sequential allocation to direct a fixed rollout budget toward arms most likely to yield informative, non-saturated groups. A preservation objective keeps useful strategy-conditioned routes accessible while successful guided behaviors are transferred to the unguided policy. Across Qwen2.5 models from 1.5B to 7B and two RL training corpora, PSRA consistently improves reasoning…
PDF arXiv
arXiv cs.LGSep 27
Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons
Kristi Topollai, Anna Choromanska
Learning-rate warmup is a standard technique in language-model training, yet its duration remains largely heuristic. Common approaches use either a fixed number of updates or a fixed fraction of the training horizon, two choices that imply very different scaling as training gets longer. When should warmup stay fixed, and when should it grow with the horizon? We address this question with a quadratic model whose modes respond differently to the peak learning rate. Warmup slows progress in directions that already contract well at the peak rate, but can remove persistent error in directions near the stability edge, with higher peak rates shifting the balance toward longer warmup durations. This yields a compact horizon scaling law that captures regimes ranging from essentially no warmup, through fixed-duration warmup, to durations that grow with the training horizon, and explains how the preferred regime changes with peak learning rate. Because the law captures the tradeoff between giving up early progress and improving the trajectory that follows, it can be fit using shorter runs and used to predict warmup at substantially longer horizons. Together, our results explain several…
PDF arXiv
arXiv cs.LGSep 26
Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors
Zhongxuan Liu, Yue Kang, Thomas C. M. Lee
Low-rank matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommodate unknown links without directly exploiting matrix or tensor rank. We address this gap by studying stochastic matrix and tensor bandits with an unknown shared Lipschitz link and a low-rank index parameter under known regular candidate distributions and finite-variance noise. For monotone links, T-ESTOR combines robust, rank-adaptive Stein estimation with epoch-based greedy selection. Under exact selected-score access and a uniformly positive selected-design Stein signal, it achieves square-root regret with dimension dependence determined by the low-rank structure. For every admissible design, the monotone lower bound matches the rank, dimension, and horizon dependence up to logarithmic factors at large horizons, for fixed menu size and model/design constants. For nonmonotone links under a nonzero base-law Stein signal, T-BSTOR combines structured estimation with robust bin-based learning and attains the optimal $\widetilde{O}(T^{2/3})$ horizon rate for fixed dimensions, menu size, and model/design constants. Synthetic and…
PDF arXiv
arXiv cs.LGSep 26
From Static Policies to Adaptive Priors in Offline Reinforcement Learning
Tianwei Ni, Vineet Jain, Akash Karthikeyan, Pierre-Luc Bacon
Offline reinforcement learning (RL) has traditionally focused on learning policies for direct deployment under conservative objectives, where uncertainty outside the offline dataset is treated pessimistically to ensure robustness. We argue that this formulation becomes incomplete when an offline-trained policy is subsequently updated through online interaction, as increasingly occurs in modern intelligent systems through test-time adaptation and online fine-tuning. This position paper argues that, in such settings, the objective of offline RL should extend beyond immediate deployment and instead prioritize learning adaptive policy priors: policies that preserve the capacity to improve during subsequent interaction through memory, exploration, and self-correction. We formalize this perspective as adaptive offline reinforcement learning (AORL), distinguish it from offline-to-online RL, and explain why adaptability becomes important under distributional shift, limited dataset coverage, and changing test-time conditions. We further discuss Bayesian offline RL as one principled direction for constructing adaptive policy priors by preserving epistemic uncertainty over plausible…
PDF arXiv
arXiv cs.LGSep 26
Saturation-Insensitive Dueling Bandits with General Function Approximation
Chenggong Zhang, Xuheng Li, Qiwei Di, Weitong Zhang, Quanquan Gu
We study contextual dueling bandits with general function approximation under the Bradley-Terry-Luce (BTL) preference model. A key challenge in this setting is the saturation of the preference model: when the current reward model can already distinguish two actions with high confidence, the resulting preference feedback becomes weakly informative, making it difficult to further improve reward estimation. Consequently, existing sample-complexity analyses often depend on the inverse-derivative factor $1 / σ'[Δ_{r^\ast}]$ which can be prohibitively large when the link function $σ$ saturates for large reward gaps $Δ_{r^\ast}$. To address this issue, we introduce `SI-CDB`, an algorithm that selects opponent arms using a carefully designed heuristic for arm selection. This design enables saturation-insensitive reward learning and recovers the near-optimal dependence for linear reward classes, eliminating the unfavorable $1/σ'(\cdot)$ factor. The core of our analysis is a localized Eluder dimension framework tailored to dueling bandits with general function approximation. Our theoretical results also explain why two-arm regret analysis is crucial for improving single-arm performance in…
PDF arXiv
arXiv cs.LGSep 26
GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
Weixian Waylon Li, Jiaxin Zhang, Han Zhou, Chengzu Li, Ke Wang +2
Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipelines, however, rely on a handful of hand-written games and on advantage estimators tied to them, so both the supply of games and the advantage estimate on a large corpus limit scaling. We present GameSmith, which scales both. An LLM synthesises games inside templates whose reward, observation, and hidden-information code is fixed. Each game is verified by seed-paired replay and by an independent re-implementation of its specification, then expanded into encoding, rule, and size variants, giving 26 new games in 29 families and 336 verified variants from the three SPIRAL templates. The model is distilled from the self-play of a larger teacher (Qwen3-32B) on these games and then trained by self-play reinforcement learning with CRAB, an advantage estimator that credits each decision against a shrinkage estimate of the expected return of its position and is defined on every variant. On Qwen3-4B-Base, distillation raises the 13-benchmark mean pass@1 from 45.5 to 62.5, above the three SPIRAL games at the same…
PDF arXiv

Papers

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable336 papers38 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl190 papers30 this week
optimal regret · near optimal · bandits221 papers23 this week
reinforcement learning rl · reinforcement learning · markov decision processes108 papers15 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers12 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.AISep 27
The Model Knows Another Way: Strategy Switching for Effective RLVR Exploration
Jin Cui, Xinyue Long, Boran Zhao, Pengju Ren, Hao Dong
Reinforcement learning with verifiable rewards (RLVR) is often limited by insufficient exploration: difficult problems can yield uniformly incorrect rollout groups and therefore little learning signal. We show that such failures need not reflect missing capability. Instead, finite sampling often concentrates on a problem-specific dominant reasoning strategy while leaving alternative strategies already supported by the model unexplored. Moreover, the accessibility of these strategies evolves during RL: some are internalized into autonomous behavior, while others become difficult to elicit before being absorbed. Motivated by these observations, we introduce Problem--Strategy Rollout Allocation (PSRA), which treats unguided and strategy-conditioned prompts as competing exploration arms and uses Bayesian sequential allocation to direct a fixed rollout budget toward arms most likely to yield informative, non-saturated groups. A preservation objective keeps useful strategy-conditioned routes accessible while successful guided behaviors are transferred to the unguided policy. Across Qwen2.5 models from 1.5B to 7B and two RL training corpora, PSRA consistently improves reasoning…
PDF arXiv
arXiv cs.LGSep 27
Balancing Early Performance Sacrifices with Long-Term Gains: Scaling Learning-Rate Warmup Duration Across Training Horizons
Kristi Topollai, Anna Choromanska
Learning-rate warmup is a standard technique in language-model training, yet its duration remains largely heuristic. Common approaches use either a fixed number of updates or a fixed fraction of the training horizon, two choices that imply very different scaling as training gets longer. When should warmup stay fixed, and when should it grow with the horizon? We address this question with a quadratic model whose modes respond differently to the peak learning rate. Warmup slows progress in directions that already contract well at the peak rate, but can remove persistent error in directions near the stability edge, with higher peak rates shifting the balance toward longer warmup durations. This yields a compact horizon scaling law that captures regimes ranging from essentially no warmup, through fixed-duration warmup, to durations that grow with the training horizon, and explains how the preferred regime changes with peak learning rate. Because the law captures the tradeoff between giving up early progress and improving the trajectory that follows, it can be fit using shorter runs and used to predict warmup at substantially longer horizons. Together, our results explain several…
PDF arXiv
arXiv cs.LGSep 26
Low-Rank Single-Index Bandits with Unknown Links: From Matrices to Tensors
Zhongxuan Liu, Yue Kang, Thomas C. M. Lee
Low-rank matrix and tensor bandits exploit structured interactions but typically assume a known reward link. Recent single-index bandit methods accommodate unknown links without directly exploiting matrix or tensor rank. We address this gap by studying stochastic matrix and tensor bandits with an unknown shared Lipschitz link and a low-rank index parameter under known regular candidate distributions and finite-variance noise. For monotone links, T-ESTOR combines robust, rank-adaptive Stein estimation with epoch-based greedy selection. Under exact selected-score access and a uniformly positive selected-design Stein signal, it achieves square-root regret with dimension dependence determined by the low-rank structure. For every admissible design, the monotone lower bound matches the rank, dimension, and horizon dependence up to logarithmic factors at large horizons, for fixed menu size and model/design constants. For nonmonotone links under a nonzero base-law Stein signal, T-BSTOR combines structured estimation with robust bin-based learning and attains the optimal $\widetilde{O}(T^{2/3})$ horizon rate for fixed dimensions, menu size, and model/design constants. Synthetic and…
PDF arXiv
arXiv cs.LGSep 26
From Static Policies to Adaptive Priors in Offline Reinforcement Learning
Tianwei Ni, Vineet Jain, Akash Karthikeyan, Pierre-Luc Bacon
Offline reinforcement learning (RL) has traditionally focused on learning policies for direct deployment under conservative objectives, where uncertainty outside the offline dataset is treated pessimistically to ensure robustness. We argue that this formulation becomes incomplete when an offline-trained policy is subsequently updated through online interaction, as increasingly occurs in modern intelligent systems through test-time adaptation and online fine-tuning. This position paper argues that, in such settings, the objective of offline RL should extend beyond immediate deployment and instead prioritize learning adaptive policy priors: policies that preserve the capacity to improve during subsequent interaction through memory, exploration, and self-correction. We formalize this perspective as adaptive offline reinforcement learning (AORL), distinguish it from offline-to-online RL, and explain why adaptability becomes important under distributional shift, limited dataset coverage, and changing test-time conditions. We further discuss Bayesian offline RL as one principled direction for constructing adaptive policy priors by preserving epistemic uncertainty over plausible…
PDF arXiv
arXiv cs.LGSep 26
Saturation-Insensitive Dueling Bandits with General Function Approximation
Chenggong Zhang, Xuheng Li, Qiwei Di, Weitong Zhang, Quanquan Gu
We study contextual dueling bandits with general function approximation under the Bradley-Terry-Luce (BTL) preference model. A key challenge in this setting is the saturation of the preference model: when the current reward model can already distinguish two actions with high confidence, the resulting preference feedback becomes weakly informative, making it difficult to further improve reward estimation. Consequently, existing sample-complexity analyses often depend on the inverse-derivative factor $1 / σ'[Δ_{r^\ast}]$ which can be prohibitively large when the link function $σ$ saturates for large reward gaps $Δ_{r^\ast}$. To address this issue, we introduce `SI-CDB`, an algorithm that selects opponent arms using a carefully designed heuristic for arm selection. This design enables saturation-insensitive reward learning and recovers the near-optimal dependence for linear reward classes, eliminating the unfavorable $1/σ'(\cdot)$ factor. The core of our analysis is a localized Eluder dimension framework tailored to dueling bandits with general function approximation. Our theoretical results also explain why two-arm regret analysis is crucial for improving single-arm performance in…
PDF arXiv
arXiv cs.LGSep 26
GameSmith: Scaling Zero-Sum Self-Play with Synthesised Games
Weixian Waylon Li, Jiaxin Zhang, Han Zhou, Chengzu Li, Ke Wang +2
Post-training large language models (LLMs) on two-player zero-sum games provides a verifiable reward, and the gains have been shown to transfer to general reasoning. Existing pipelines, however, rely on a handful of hand-written games and on advantage estimators tied to them, so both the supply of games and the advantage estimate on a large corpus limit scaling. We present GameSmith, which scales both. An LLM synthesises games inside templates whose reward, observation, and hidden-information code is fixed. Each game is verified by seed-paired replay and by an independent re-implementation of its specification, then expanded into encoding, rule, and size variants, giving 26 new games in 29 families and 336 verified variants from the three SPIRAL templates. The model is distilled from the self-play of a larger teacher (Qwen3-32B) on these games and then trained by self-play reinforcement learning with CRAB, an advantage estimator that credits each decision against a shrinkage estimate of the expected return of its position and is defined on every variant. On Qwen3-4B-Base, distillation raises the 13-benchmark mean pass@1 from 45.5 to 62.5, above the three SPIRAL games at the same…
PDF arXiv

Activity · 12 weeks

Fields · AI · updated 29m ago

Learning verifiable rewards

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

118papers this week−43.8% vs last week

All papers · 949 With code · 29

Newest Most relevant

856 papers this month

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.