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 papers58 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl186 papers40 this week
optimal regret · near optimal · bandits217 papers36 this week
reinforcement learning rl · reinforcement learning · markov decision processes105 papers17 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers17 this week

Topics in this field

Active contributors · 90 days

Active contributors

Activity · 12 weeks

Activity

Recent papers

All papers in Research

arXiv cs.LGOct 4
Revealing After Overwriting: An Exponential POMDP OPE Lower Bound under History-Dependent Logging
Youyu Luo, Pengzhan Zhou, Zhida Qin, Jia Wang, Zuotao Fu +2
Multi-step revealing can make off-policy evaluation tractable under memoryless logging. With history-dependent logging, state decodability and target-relevant evidence can separate. For every horizon $H\ge3$, we construct two exactly realizable POMDPs with four actions, at most four states per layer, a known logger, and a memoryless target. Action overlap, history coverage, and observation-only revealing remain bounded independently of $H$, yet the target values differ by $1/2$ and the KL divergence between the logged laws is $Θ(4^{-(H-1)})$, forcing exponential sample complexity. Logger memory makes states distinguishable, while reset erases the model-distinguishing evidence preserved by the target. A separate construction retains this barrier with common, known observation-only revealing operators. Under action and history coverage, we give a finite-class OPE guarantee using common observable value representations that remain valid at every history. The sample bound depends polynomially on their second-moment cost. In the common-operator construction, the same value direction has constant marginal decoding cost but exponential history-conditioned cost. Finally, on a fixed…
PDF arXiv
arXiv cs.LGOct 4
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage
Shuze Daniel Liu, Claire Chen, Jiuqi Wang, David Simchi-Levi
We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions and negotiations with private valuations. We introduce unilateral prescriptive concentrability and show that asymmetric information can change offline coverage through its effect on equilibrium behavior. For finite state-action spaces, we develop a pessimistic algorithm with an $\tilde{O}(1/\sqrt{n})$ exploitability rate, matching the standard sample-size dependence for fully observed minimax games. We further develop a pessimistic policy mirror descent framework, PPA-PMD, for general function approximation and obtain a unified $\tilde{O}(1/\sqrt{n} + 1/\sqrt{T})$ exploitability rate with no-regret actor updates. Together, these results provide the first theoretical framework for offline equilibrium learning under public-private information constraints.
PDF arXiv
arXiv cs.LGOct 4
Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K
Yi Hou
This paper studies GRPO at 1B scale from both directions: what estimator choices do to the learning signal, and what a degraded reward signal does to what is learned. We train OLMo-2-0425-1B on GSM8K with a from-scratch implementation and measure both sides in controlled sweeps, including a verifier-quality experiment that degrades the training reward and the test-time selector identically. Four results stand out. The prompt is the first-order decision: the zero-shot prompt leaves the base model at 0.08% (its outputs are degenerate continuations, not wrong answers), so almost no group carries a gradient, and training succeeds because the 3-shot prompt reaches 18.3%. At this scale the estimator variants sit within seed noise, with Dr. GRPO ahead on both seeds. In the off-policy regime, clipping is the whole story: training on data without a clipped ratio loses 4-6 points relative to the on-policy reference, while GRPO-style clipping and GSPO recover the loss entirely. Finally, the same weak verifier is far cheaper in RL than in test-time selection: a 10%-flip verifier leaves RL's attainable gain intact (91% and 106% retained across two seeds) where selection retains 57%, and a…
PDF arXiv
arXiv cs.LGOct 4
Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning
Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor +4
Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the decisions that produced it. We introduce Residual Visual Credit Optimization (RVCO), which treats token credit as a conserved routing problem. A controlled visual intervention yields a per-token evidence response; robust within-trajectory coordinates remove incidental scale; and a budgeted entropic router distributes a fixed amount of sequence utility according to perceptual dependence. A residual support path guarantees positive credit at every valid position, and an analytic correction restores the prescribed credit mass exactly. The resulting field is selective, bounded, full-support, and invariant to response-local score shifts, and recovers hard token selection as a limiting case. Across four model families and seven reasoning benchmarks, RVCO improves accuracy over strong RLVR baselines while maintaining late-stage optimization stability, corruption robustness, and competitive training cost. Rewards, rollouts, and the group-relative advantage estimator are unchanged; only the geometry of…
PDF arXiv
arXiv cs.CROct 4
Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense
Zahra Aref, Sheng Wei, Narayan B. Mandayam
Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets against a Deep Q-Network (DQN) attacker. We compare four defender settings: a human reward-only game operationalizing the DQN information structure, a human reward-plus-transition game operationalizing the Cognitive Hierarchy Theory-driven DQN (CHT-DQN) information structure, an automated DQN defender, and an automated CHT-DQN defender. In the reward-only game, participants receive payoff and reward feedback. In the reward-plus-transition game, they also see attacker-aware transition probabilities from the CHT-DQN model. Across 80 Mechanical Turk participants and matched automated simulations, human defenders adapted to outcomes in a way the automated defenders did not: they were more likely to reselect a node after a successful defense than after a failure, in both games, an asymmetry we interpret as consistent with Prospect Theory and Cumulative Prospect Theory. The 40-round average also…
PDF arXiv
arXiv cs.LGCodeOct 4▲ 2
CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery
Tao Feng, Fangxu Yu, Zijie Lei, Jiaru Zou, Changjiang Jiang +3
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large language model (LLM) can reuse previous solutions in context, but cannot update the model from its successes and failures on the test problem. Reinforcement learning (RL) enables such adaptation; however, strongly favoring high-reward trajectories may suppress low-reward yet potentially promising directions too early. We introduce CURIO, a curiosity-driven test-time learning framework that complements task feedback with an Intrinsic Curiosity World Model (ICWM). The ICWM learns transitions in the policy's hidden-state representation and supplies prediction-error bonuses at sampled tokens outside the policy's top-k choices. Epoch normalization and an annealed weight regulate their contribution to the policy update. On six mathematical discovery tasks and single-cell denoising with Qwen3 backbones from 8B to 235B, three-run means improve over a matched task-only RL control on five mathematical objectives, match the best reported performance on Circle Packing, and improve denoising Score and mean squared error (MSE) on both…
PDF arXiv Code

Papers

Topics in this field

learning verifiable rewards · reinforcement learning rl · reinforcement learning verifiable329 papers58 this week
offline reinforcement learning · offline reinforcement · reinforcement learning rl186 papers40 this week
optimal regret · near optimal · bandits217 papers36 this week
reinforcement learning rl · reinforcement learning · markov decision processes105 papers17 this week
policy gradient · reinforcement learning rl · reinforcement learning verifiable94 papers17 this week

Active contributors · 90 days

Recent papers

All papers in Research

arXiv cs.LGOct 4
Revealing After Overwriting: An Exponential POMDP OPE Lower Bound under History-Dependent Logging
Youyu Luo, Pengzhan Zhou, Zhida Qin, Jia Wang, Zuotao Fu +2
Multi-step revealing can make off-policy evaluation tractable under memoryless logging. With history-dependent logging, state decodability and target-relevant evidence can separate. For every horizon $H\ge3$, we construct two exactly realizable POMDPs with four actions, at most four states per layer, a known logger, and a memoryless target. Action overlap, history coverage, and observation-only revealing remain bounded independently of $H$, yet the target values differ by $1/2$ and the KL divergence between the logged laws is $Θ(4^{-(H-1)})$, forcing exponential sample complexity. Logger memory makes states distinguishable, while reset erases the model-distinguishing evidence preserved by the target. A separate construction retains this barrier with common, known observation-only revealing operators. Under action and history coverage, we give a finite-class OPE guarantee using common observable value representations that remain valid at every history. The sample bound depends polynomially on their second-moment cost. In the common-operator construction, the same value direction has constant marginal decoding cost but exponential history-conditioned cost. Finally, on a fixed…
PDF arXiv
arXiv cs.LGOct 4
Pessimistic Minimax Learning for Public-Private Information Games under Unilateral Coverage
Shuze Daniel Liu, Claire Chen, Jiuqi Wang, David Simchi-Levi
We study offline learning in two-player zero-sum contextual games with public and private information, motivated by strategic settings such as auctions and negotiations with private valuations. We introduce unilateral prescriptive concentrability and show that asymmetric information can change offline coverage through its effect on equilibrium behavior. For finite state-action spaces, we develop a pessimistic algorithm with an $\tilde{O}(1/\sqrt{n})$ exploitability rate, matching the standard sample-size dependence for fully observed minimax games. We further develop a pessimistic policy mirror descent framework, PPA-PMD, for general function approximation and obtain a unified $\tilde{O}(1/\sqrt{n} + 1/\sqrt{T})$ exploitability rate with no-regret actor updates. Together, these results provide the first theoretical framework for offline equilibrium learning under public-private information constraints.
PDF arXiv
arXiv cs.LGOct 4
Prompt Dominance and Asymmetric Verifier Costs: Empirical Ablations of GRPO at 1B Scale on GSM8K
Yi Hou
This paper studies GRPO at 1B scale from both directions: what estimator choices do to the learning signal, and what a degraded reward signal does to what is learned. We train OLMo-2-0425-1B on GSM8K with a from-scratch implementation and measure both sides in controlled sweeps, including a verifier-quality experiment that degrades the training reward and the test-time selector identically. Four results stand out. The prompt is the first-order decision: the zero-shot prompt leaves the base model at 0.08% (its outputs are degenerate continuations, not wrong answers), so almost no group carries a gradient, and training succeeds because the 3-shot prompt reaches 18.3%. At this scale the estimator variants sit within seed noise, with Dr. GRPO ahead on both seeds. In the off-policy regime, clipping is the whole story: training on data without a clipped ratio loses 4-6 points relative to the on-policy reference, while GRPO-style clipping and GSPO recover the loss entirely. Finally, the same weak verifier is far cheaper in RL than in test-time selection: a 10%-flip verifier leaves RL's attainable gain intact (91% and 106% retained across two seeds) where selection retains 57%, and a…
PDF arXiv
arXiv cs.LGOct 4
Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning
Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor +4
Reinforcement learning with verifiable rewards scales multimodal reasoning, but an outcome reward says how much a trajectory is worth, not how that value should be spread over the decisions that produced it. We introduce Residual Visual Credit Optimization (RVCO), which treats token credit as a conserved routing problem. A controlled visual intervention yields a per-token evidence response; robust within-trajectory coordinates remove incidental scale; and a budgeted entropic router distributes a fixed amount of sequence utility according to perceptual dependence. A residual support path guarantees positive credit at every valid position, and an analytic correction restores the prescribed credit mass exactly. The resulting field is selective, bounded, full-support, and invariant to response-local score shifts, and recovers hard token selection as a limiting case. Across four model families and seven reasoning benchmarks, RVCO improves accuracy over strong RLVR baselines while maintaining late-stage optimization stability, corruption robustness, and competitive training cost. Rewards, rollouts, and the group-relative advantage estimator are unchanged; only the geometry of…
PDF arXiv
arXiv cs.CROct 4
Bounded Reasoning: Cognitive Hierarchy in Human-versus-AI Cyber Defense
Zahra Aref, Sheng Wei, Narayan B. Mandayam
Human-agent evaluations often compress interaction into a single performance score, even when human and automated policies adapt differently over time. We study this in a sequential cyber-defense game on an attack graph, where a human or reinforcement-learning defender protects cloud assets against a Deep Q-Network (DQN) attacker. We compare four defender settings: a human reward-only game operationalizing the DQN information structure, a human reward-plus-transition game operationalizing the Cognitive Hierarchy Theory-driven DQN (CHT-DQN) information structure, an automated DQN defender, and an automated CHT-DQN defender. In the reward-only game, participants receive payoff and reward feedback. In the reward-plus-transition game, they also see attacker-aware transition probabilities from the CHT-DQN model. Across 80 Mechanical Turk participants and matched automated simulations, human defenders adapted to outcomes in a way the automated defenders did not: they were more likely to reselect a node after a successful defense than after a failure, in both games, an asymmetry we interpret as consistent with Prospect Theory and Cumulative Prospect Theory. The 40-round average also…
PDF arXiv
arXiv cs.LGCodeOct 4▲ 2
CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery
Tao Feng, Fangxu Yu, Zijie Lei, Jiaru Zou, Changjiang Jiang +3
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large language model (LLM) can reuse previous solutions in context, but cannot update the model from its successes and failures on the test problem. Reinforcement learning (RL) enables such adaptation; however, strongly favoring high-reward trajectories may suppress low-reward yet potentially promising directions too early. We introduce CURIO, a curiosity-driven test-time learning framework that complements task feedback with an Intrinsic Curiosity World Model (ICWM). The ICWM learns transitions in the policy's hidden-state representation and supplies prediction-error bonuses at sampled tokens outside the policy's top-k choices. Epoch normalization and an annealed weight regulate their contribution to the policy update. On six mathematical discovery tasks and single-cell denoising with Qwen3 backbones from 8B to 235B, three-run means improve over a matched task-only RL control on five mathematical objectives, match the best reported performance on Circle Packing, and improve denoising Score and mean squared error (MSE) on both…
PDF arXiv Code

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 27m ago

Learning verifiable rewards

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

168papers this week−13.8% vs last week

All papers · 931 With code · 28

Newest Most relevant

879 papers this month