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 degrade 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, reducing task appropriateness.
- 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 verifiable329 papers49 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl186 papers31 this week
optimal regret · near optimal · bandits217 papers29 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers14 this week
reinforcement learning rl · reinforcement learning · markov decision processes105 papers13 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.AIOct 2
FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang +2
Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier allocation, and update budget. Three coupled issues remain unresolved. A future-risk model trained from behavior trajectories need not estimate the risk induced by the controller that will be deployed; a score calibrated on logged state-action pairs can become miscalibrated after selective action choice; and independent per-resource minimum costs do not in general certify a feasible multi-resource continuation. We introduce FSPO, a feedback-state controller for budgeted LLM RL post-training that addresses these issues jointly. FSPO learns a policy-consistent risk-to-go model whose Bellman target follows the same frozen controller used for future decisions, together with a long-horizon utility model. Decision-conditioned trajectory calibration (DCTC) calibrates risk on cross-fitted trajectories generated by actions selected by provisional controllers. A Pareto resource continuation certificate (PRCC) admits an action only when a non-dominated cumulative reservation remains feasible over the residual horizon.…
PDF arXiv
arXiv cs.AICodeOct 2▲ 33
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
Yuxuan Fan, Jaehong Yoon
Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requirements. However, rubric judges can assign a high criterion score even when the information or action it requires is absent from the response, a failure mode we term Vacuous Credit. Such awards persist after the required information is removed and can reverse the sign of a response's GRPO advantage. To address this problem, we introduce MetaRubric, which alternates evidence-aware policy optimization with response-guided rubric adaptation. We construct counterfactual counterparts by changing one task-relevant fact in each prompt. During policy optimization, credit is assigned only when the response contains sufficient evidence to satisfy the required rubric criterion. After each policy-optimization stage, current policy responses guide revisions to original and counterfactual criteria while preserving the meaning of the original prompt's initial rubric as interpreted under each prompt's facts. We also adapt criterion weights at stage boundaries to better address observed policy errors. Across multiple backbones, MetaRubric improves…
PDF arXiv Code
arXiv cs.LGOct 2
Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
Khang Luong, Dinh Thai Son, Hoang Ta, Hung The Tran, Tuan Quang Dam
We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a single bit indicating whether the sampled reward belongs to that set. We consider a distribution-free finite-variance setting with arm-wise localization, where direct empirical mean estimation is no longer available and clipping becomes unavoidable. We first formulate a time-uniform 1-bit mean-estimation primitive based on randomized threshold queries and a clipped tail-integral identity. We then embed this primitive into candidate-challenger best-arm identification algorithms. A fixed-clipping algorithm gives a simple anytime $(ε,δ)$-PAC guarantee, while a phased adaptive-clipping algorithm matches the clipping level to the current resolution and yields a gap-adaptive sample complexity. We also prove a $K$-arm worst-case information-theoretic lower bound showing that the logarithmic penalty caused by finite-variance 1-bit feedback is intrinsic. This bound matches the leading dependence of the phased algorithm up to lower-order $\log\log$ factors.
PDF arXiv
arXiv cs.LGOct 2▲ 10
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Yu Li, Hiroaki Hayashi +1
Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the agent's belief at action time invisible to the gradient. We introduce Prospective Hindsight (PH), a self-calibrating training principle that augments any retrospective base method with a signal derived from the gap between the agent's prospective prediction (before feedback) and the retrospective evaluation (after feedback). This per-rollout surprise identifies samples where the agent's self-model is most inaccurate and amplifies their gradient contribution through a stop-gradient surprise-weighted advantage. Since the prospective predictor shares parameters with the policy, the two co-evolve, progressively shifting focus to the agent's remaining blind spots. We connect this principle to a privileged-information gap and show that minimizing the surprise residual provides a descent pathway on the agent's miscalibration rate; calibration thus emerges as a byproduct of optimization rather than from an added objective. On single-turn verifiable tasks and a multi-turn personal-agent task (under GRPO, on-policy…
PDF arXiv
arXiv cs.LGOct 2
Bellman Error Minimization Via Linear Programming Normalization
Haining Yu
This paper proposes a new functional approximation approach to reduce Bellman error in high-dimensional dynamic programming and Reinforcement Learning problems. Using a classic dynamic programming problem (network capacity control in revenue management) as the motivational example, the paper illustrates that deep neural networks and linear programming approximation algorithms can be combined to derive approximate solutions to dynamic programming problems. Simulation results show the proposed approximation algorithms achieves competitive performance when compared with benchmark.
PDF arXiv
arXiv cs.LGOct 1
Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
Dongsu Lee, Haoran Xu, Amy Zhang
Offline multi-agent reinforcement learning (MARL) faces a persistent trade-off. Expressive generative policies can represent multi-modal coordination in the data, but cannot distinguish high-value regions, while value-optimized policies exploit the learned Q-function but collapse the multi-modal into a single dominant mode. A single agent's mode collapse can break joint coordination, and simultaneous drift across agents can push the joint policy into unseen regions of the action space. We propose scalable coordination via optimal unified transport (SCOUT), the first offline MARL framework to combine a generative foundation model with a learned value function through test-time action refinement. SCOUT trains two decoupled components: a flow-matching behavioral prior and a decomposed value function. At test-time, it transports behavioral samples toward high-value regions via Stein variational gradient descent. The number of transport steps controls adaptive test-time scaling, replacing a fixed regularization coefficient. Under the individual-global-max (IGM) principle, we prove a single-term KL bound on the joint soft-value gap that vanishes as transport converges, with an…
PDF arXiv

Papers

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable329 papers49 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl186 papers31 this week
optimal regret · near optimal · bandits217 papers29 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers14 this week
reinforcement learning rl · reinforcement learning · markov decision processes105 papers13 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.AIOct 2
FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training
Miaobo Hu, Shuhao Hu, Xiaobo Guo, Xin Wang, Bokun Wang +2
Adaptive LLM reinforcement-learning post-training changes multiple training actuators online, including rollout temperature, group size, clipping, KL regularization, verifier allocation, and update budget. Three coupled issues remain unresolved. A future-risk model trained from behavior trajectories need not estimate the risk induced by the controller that will be deployed; a score calibrated on logged state-action pairs can become miscalibrated after selective action choice; and independent per-resource minimum costs do not in general certify a feasible multi-resource continuation. We introduce FSPO, a feedback-state controller for budgeted LLM RL post-training that addresses these issues jointly. FSPO learns a policy-consistent risk-to-go model whose Bellman target follows the same frozen controller used for future decisions, together with a long-horizon utility model. Decision-conditioned trajectory calibration (DCTC) calibrates risk on cross-fitted trajectories generated by actions selected by provisional controllers. A Pareto resource continuation certificate (PRCC) admits an action only when a non-dominated cumulative reservation remains feasible over the residual horizon.…
PDF arXiv
arXiv cs.AICodeOct 2▲ 33
MetaRubric: Learning to Reward for Rubric-Based Reinforcement Learning
Yuxuan Fan, Jaehong Yoon
Rubric-based reinforcement learning extends reward-driven optimization to open-ended tasks by assigning partial credit to individual response requirements. However, rubric judges can assign a high criterion score even when the information or action it requires is absent from the response, a failure mode we term Vacuous Credit. Such awards persist after the required information is removed and can reverse the sign of a response's GRPO advantage. To address this problem, we introduce MetaRubric, which alternates evidence-aware policy optimization with response-guided rubric adaptation. We construct counterfactual counterparts by changing one task-relevant fact in each prompt. During policy optimization, credit is assigned only when the response contains sufficient evidence to satisfy the required rubric criterion. After each policy-optimization stage, current policy responses guide revisions to original and counterfactual criteria while preserving the meaning of the original prompt's initial rubric as interpreted under each prompt's facts. We also adapt criterion weights at stage boundaries to better address observed policy errors. Across multiple backbones, MetaRubric improves…
PDF arXiv Code
arXiv cs.LGOct 2
Nearly Optimal Fixed-Confidence Best-Arm Identification with 1-Bit Feedback
Khang Luong, Dinh Thai Son, Hoang Ta, Hung The Tran, Tuan Quang Dam
We study fixed-confidence best-arm identification under strict 1-bit feedback constraints. At each round, the learner selects an arm and a query set, and receives only a single bit indicating whether the sampled reward belongs to that set. We consider a distribution-free finite-variance setting with arm-wise localization, where direct empirical mean estimation is no longer available and clipping becomes unavoidable. We first formulate a time-uniform 1-bit mean-estimation primitive based on randomized threshold queries and a clipped tail-integral identity. We then embed this primitive into candidate-challenger best-arm identification algorithms. A fixed-clipping algorithm gives a simple anytime $(ε,δ)$-PAC guarantee, while a phased adaptive-clipping algorithm matches the clipping level to the current resolution and yields a gap-adaptive sample complexity. We also prove a $K$-arm worst-case information-theoretic lower bound showing that the logarithmic penalty caused by finite-variance 1-bit feedback is intrinsic. This bound matches the leading dependence of the phased algorithm up to lower-order $\log\log$ factors.
PDF arXiv
arXiv cs.LGOct 2▲ 10
Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps
Jiaxin Zhang, Xiangyu Peng, Qinglin Chen, Yu Li, Hiroaki Hayashi +1
Reinforcement learning for long-horizon agents relies on purely retrospective training signals: credit is assigned only after observing environmental consequences, leaving the agent's belief at action time invisible to the gradient. We introduce Prospective Hindsight (PH), a self-calibrating training principle that augments any retrospective base method with a signal derived from the gap between the agent's prospective prediction (before feedback) and the retrospective evaluation (after feedback). This per-rollout surprise identifies samples where the agent's self-model is most inaccurate and amplifies their gradient contribution through a stop-gradient surprise-weighted advantage. Since the prospective predictor shares parameters with the policy, the two co-evolve, progressively shifting focus to the agent's remaining blind spots. We connect this principle to a privileged-information gap and show that minimizing the surprise residual provides a descent pathway on the agent's miscalibration rate; calibration thus emerges as a byproduct of optimization rather than from an added objective. On single-turn verifiable tasks and a multi-turn personal-agent task (under GRPO, on-policy…
PDF arXiv
arXiv cs.LGOct 2
Bellman Error Minimization Via Linear Programming Normalization
Haining Yu
This paper proposes a new functional approximation approach to reduce Bellman error in high-dimensional dynamic programming and Reinforcement Learning problems. Using a classic dynamic programming problem (network capacity control in revenue management) as the motivational example, the paper illustrates that deep neural networks and linear programming approximation algorithms can be combined to derive approximate solutions to dynamic programming problems. Simulation results show the proposed approximation algorithms achieves competitive performance when compared with benchmark.
PDF arXiv
arXiv cs.LGOct 1
Test-time Multi-agent Coordination by Decomposed Value Gradient Flow
Dongsu Lee, Haoran Xu, Amy Zhang
Offline multi-agent reinforcement learning (MARL) faces a persistent trade-off. Expressive generative policies can represent multi-modal coordination in the data, but cannot distinguish high-value regions, while value-optimized policies exploit the learned Q-function but collapse the multi-modal into a single dominant mode. A single agent's mode collapse can break joint coordination, and simultaneous drift across agents can push the joint policy into unseen regions of the action space. We propose scalable coordination via optimal unified transport (SCOUT), the first offline MARL framework to combine a generative foundation model with a learned value function through test-time action refinement. SCOUT trains two decoupled components: a flow-matching behavioral prior and a decomposed value function. At test-time, it transports behavioral samples toward high-value regions via Stein variational gradient descent. The number of transport steps controls adaptive test-time scaling, replacing a fixed regularization coefficient. Under the individual-global-max (IGM) principle, we prove a single-term KL bound on the joint soft-value gap that vanishes as transport converges, with an…
PDF arXiv

Activity · 12 weeks

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 degrade 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, reducing task appropriateness.
- 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 22m ago

Learning verifiable rewards

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

136papers this week−33.0% vs last week

All papers · 931 With code · 29

Newest Most relevant

870 papers this month