REVIEW 15 cited by
Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Reinforcement learning with verifiable rewards (RLVR) has demonstrated significant success in enhancing mathematical reasoning and coding performance of large language models (LLMs), especially when structured reference answers are accessible for verification. However, its extension to broader, less structured domains remains unexplored. In this work, we investigate the effectiveness and scalability of RLVR across diverse real-world domains including medicine, chemistry, psychology, economics, and education, where structured reference answers are typically unavailable. We reveal that binary verification judgments on broad-domain tasks exhibit high consistency across various LLMs provided expert-written reference answers exist. Motivated by this finding, we utilize a generative scoring technique that yields soft, model-based reward signals to overcome limitations posed by binary verifications, especially in free-form, unstructured answer scenarios. We further demonstrate the feasibility of training cross-domain generative reward models using relatively small (7B) LLMs without the need for extensive domain-specific annotation. Through comprehensive experiments, our RLVR framework establishes clear performance gains, significantly outperforming state-of-the-art open-source aligned models such as Qwen2.5-72B and DeepSeek-R1-Distill-Qwen-32B across domains in free-form settings. Our approach notably enhances the robustness, flexibility, and scalability of RLVR, representing a substantial step towards practical reinforcement learning applications in complex, noisy-label scenarios.
Forward citations
Cited by 15 Pith papers
-
Student-Centered Distillation Narrows the Agentic Gap Between Small and Large LLMs
A 7B LLM agent trained with student-led distillation and one-step teacher corrections nearly matches a 72B teacher on reasoning and tool-use benchmarks.
-
Gradient Immunity: Null-Space Resistance to Malicious Fine-Tuning
Calibrating a null-space gate to fully cover the defender's harmful data keeps post-fine-tuning attack success at pre-release levels, but this is a coverage and calibration consequence rather than a tested defense on ...
-
MedUPS: Towards Diagnostic Assistance in Uncommon Medical Cases with Large Language Models
Mid-stream alignment on next-step clinical decisions (MedUPS) improves LLM next-step accuracy on uncommon cases, but the size of the gain depends substantially on which LLM judge does the scoring.
-
LH-Bench: Skill-Grounded Evaluation of Long-Horizon Agents on Subjective Enterprise Tasks
Expert-authored dual-use skills make LLM judges more reliable on subjective long-horizon enterprise agent tasks than LLM-authored rubrics, with human preferences confirming the main ranking boundary.
-
CLARity: Reasoning Consistency Alone Can Teach Reinforced Experts
A consistency reward parsed by a 7B LLM, plus a two-stage refine-then-monitor pipeline and reformulated easy questions, improves MCQ-RL accuracy-with-consistency in law and medicine (58.9 vs 51.4 average Acc+).
-
One Token to Fool LLM-as-a-Judge
LLM reward models falsely accept empty 'master key' responses such as ':' or 'Thought process:' across many models, and a fine-tuning defense reduces these false positives to near zero.
-
Energy-Based Transformers are Scalable Learners and Thinkers
Energy-Based Transformers learn to predict by gradient-descent minimization of a learned energy function, and the paper reports faster pretraining scaling and inference-time thinking gains over Transformer++ and Diffu...
-
Consistent Paths Lead to Truth: Self-Rewarding Reinforcement Learning for LLM Reasoning
CoVo trains LLMs with a self-generated reward based on the consistency and volatility of intermediate reasoning states, matching supervised RL performance without external labels.
-
ReSpace: Text-Driven Autoregressive 3D Indoor Scene Synthesis and Editing
ReSpace is an autoregressive LLM framework for text-driven 3D indoor scene editing and synthesis, using a structured JSON scene representation and a voxelization-based layout metric.
-
Reasoning Like an Economist: Post-Training on Economic Problems Induces Strategic Generalization in LLMs
Post-training an LLM on economic reasoning problems improves accuracy on economic benchmarks and, without game-specific training, raises its Nash equilibrium frequency and win rates in strategic games.
-
Training LLMs for EHR-Based Reasoning Tasks via Reinforcement Learning
A 3B model trained with a small SFT warm-up followed by verifiable-reward RL matches or exceeds far larger models on EHR-based medical calculation, trial matching, and diagnosis tasks.
-
Interpretable Electrophysiological Features of Resting-State EEG Capture Cortical Network Dynamics in Parkinsons Disease
Standard spectral/synchronization EEG features best separate PD medication states, while dynamical network descriptors compete for PD-versus-control discrimination under LOSO transformer classification.
-
Reverse Browser: Vector-Image-to-Code Generator
An open-weights system that turns vector images of web designs into HTML/CSS, with new datasets and a multi-scale pixel metric, though accuracy remains below production quality.
-
From Emergence to Control: Probing and Modulating Self-Reflection in Language Models
Self-reflection in LLMs can be steered up or down by a single activation-space vector, improving accuracy when amplified and cutting output length when suppressed.
-
Reinforcement Learning Optimization for Large-Scale Learning: An Efficient and User-Friendly Scaling Library
ROLL is a distributed RL training library for LLMs with sample-level rollout scheduling and flexible device mapping, demonstrated on RLVR and agentic tasks but without baseline or scaling measurements.
Discussion (0). Sign in to comment.