Structured cognitive-episode features from LRM reasoning traces, combined with item semantics, improve human item-difficulty prediction and show harder items drive more implementation-centered, iterative solving.
Self-rewarding correction for mathematical reasoning.arXiv preprint arXiv:2502.19613
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
GuardedRepair uses guarded best-of-N repair with symbolic checks, semantic diagnostics, and conservative policies to selectively replace LLM reasoning traces, raising GSM8K accuracy from 95.60% to 96.89% and ASDiv from 78.40% to 87.60% without breaking correct cases.
Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.
LightReasoner distills supervision signals from SLM-LLM behavioral divergence to improve LLM reasoning on math benchmarks with up to 28.1% accuracy gains and 90-99% reductions in resources.
PROF curates RL training data via PRM-ORM consistency to improve both final-answer accuracy and intermediate reasoning quality while reducing reliance on strong process reward models.
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
A method internalizes outcome supervision into process supervision by extracting step-level learning signals from failed reasoning trajectories during reinforcement learning.
ACE introduces a solver-adversary loop where an LLM generates both candidate programs and adversarial tests, using execution outcomes for preference optimization to achieve 3-7% pass@1 gains on code benchmarks without ground-truth code.
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.
rePIRL learns token-level process rewards for LLM reasoning via a guided-cost-learning-style IRL objective, and shows these rewards improve reasoning policies on math/coding benchmarks.
citing papers explorer
-
Cognitive Episodes in LLM Reasoning Traces Enable Interpretable Human Item Difficulty Prediction
Structured cognitive-episode features from LRM reasoning traces, combined with item semantics, improve human item-difficulty prediction and show harder items drive more implementation-centered, iterative solving.
-
ReSum: Synergizing LLM Reasoning and Summarization with Reinforcement Learning
ReSum's contrastive RL branching on self-summarization points improves LLM math reasoning accuracy by about 4% and shortens rollouts by about 18.6% across tested backbones.
-
Guarded Repair for Harm-Aware Post-hoc Replacement of LLM Mathematical Reasoning
GuardedRepair uses guarded best-of-N repair with symbolic checks, semantic diagnostics, and conservative policies to selectively replace LLM reasoning traces, raising GSM8K accuracy from 95.60% to 96.89% and ASDiv from 78.40% to 87.60% without breaking correct cases.
-
Can LLMs Learn to Reason Robustly under Noisy Supervision?
Online Label Refinement lets LLMs learn robust reasoning from noisy supervision by correcting labels when majority answers show rising rollout success and stable history, delivering 3-4% gains on math and reasoning benchmarks even at high noise levels.
-
LightReasoner: Can Small Language Models Teach Large Language Models Reasoning?
LightReasoner distills supervision signals from SLM-LLM behavioral divergence to improve LLM reasoning on math benchmarks with up to 28.1% accuracy gains and 90-99% reductions in resources.
-
Beyond Correctness: Harmonizing Process and Outcome Rewards through RL Training
PROF curates RL training data via PRM-ORM consistency to improve both final-answer accuracy and intermediate reasoning quality while reducing reliance on strong process reward models.
-
Modularized Reinforcement Learning on LLMs: From MDP Creation to Exploration and Learning
Survey mapping RL techniques onto LLM training and highlighting gaps in value-based, off-policy, and bootstrapping methods.
-
Trust Region On-Policy Distillation
TrOPD stabilizes on-policy distillation for LLMs with trust-region learning, outlier estimation, and off-policy guidance, outperforming prior OPD methods on reasoning and code benchmarks.
-
Internalizing Outcome Supervision into Process Supervision: A New Paradigm for Reinforcement Learning for Reasoning
A method internalizes outcome supervision into process supervision by extracting step-level learning signals from failed reasoning trajectories during reinforcement learning.
-
ACE: Self-Evolving LLM Coding Framework via Adversarial Unit Test Generation and Preference Optimization
ACE introduces a solver-adversary loop where an LLM generates both candidate programs and adversarial tests, using execution outcomes for preference optimization to achieve 3-7% pass@1 gains on code benchmarks without ground-truth code.
-
The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes
A literature survey that introduces a taxonomy for LLM reasoning paradigms, analyzes methodological trends, and synthesizes failure modes from over 300 papers.
-
rePIRL: Learn PRM with Inverse RL for LLM Reasoning
rePIRL learns token-level process rewards for LLM reasoning via a guided-cost-learning-style IRL objective, and shows these rewards improve reasoning policies on math/coding benchmarks.