FeynmanBench is the first benchmark for evaluating multimodal LLMs on diagrammatic reasoning with Feynman diagrams, revealing systematic failures in enforcing physical constraints and global topology.
hub
O lympiad B ench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problems
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
hub tools
citation-role summary
dataset 2
background 1
method 1
citation-polarity summary
representative citing papers
Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.
OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
Frontier LLMs struggle to discriminate data uncertainty from model uncertainty even when accurate, but a new benchmark and lightweight RL strategy improve attribution without sacrificing answer accuracy.
Evo-L2S uses multi-objective evolutionary model merging to produce reasoning models that cut generated chain-of-thought length by over 50% while preserving or improving accuracy on math benchmarks.
HölderPO unifies token aggregation in GRPO via the Hölder mean with dynamic p annealing, reporting 54.9% average math-benchmark accuracy and 93.8% ALFWorld success.
EvoTD applies crossover for skill composition and parametric mutation for complexity scaling, filtered by a Zone of Proximal Development, to generate tasks that improve LLM reasoning generalization across models.
SORT turns all-wrong prompts into selective learning signals by weighting tokens more predictable under plan guidance from reference solutions, improving over GRPO on reasoning benchmarks especially for weaker models.
RLCM trains LLMs with a margin-enhanced process reward that widens the gap between correct and incorrect reasoning steps, improving calibration on math, code, logic, and science tasks without hurting accuracy.
DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.
PDDL planning problems are used to generate about one million precise reasoning steps for training Process Reward Models, and adding this data to existing datasets improves LLM performance on both mathematical and non-mathematical reasoning benchmarks.
MEDS improves LLM RL performance by up to 4.13 pass@1 and 4.37 pass@128 points by dynamically penalizing rollouts matching prevalent historical error clusters identified via memory-stored representations and density clustering.
NPR trains LLMs to reason in parallel via self-distilled RL, delivering up to 24.5% performance gains and 4.6x speedups with 100% genuine parallel execution on reasoning benchmarks.
Entropy Ratio Clipping introduces a global entropy-ratio constraint that stabilizes RL policy updates in LLM post-training beyond local PPO clipping.
PRIME enables online process reward model updates in LLM RL using implicit rewards from rollouts and outcome labels, yielding 15.1% average gains on reasoning benchmarks and surpassing a stronger instruct model with 10% of the data.
ExpThink applies experience-tracked rewards and correct-count normalized advantages in RL to compress CoT reasoning, cutting length up to 77% while raising accuracy and efficiency ratio on math benchmarks.
MathArena is a maintained platform evaluating LLMs across olympiad problems, proofs, research questions, and formal proofs, with GPT-5.5 reaching 98% on 2026 USAMO and 74% on research-level tasks.
OGER adds an auxiliary exploration reward built from offline trajectories and model entropy to hybrid RL training, yielding gains on math reasoning benchmarks and out-of-domain generalization.
TRACE aggregates answer consistency and confidence trajectory over multiple reasoning steps to decide when to halt inference, reducing token usage by 25-30% while keeping accuracy within 1-2% of full reasoning.
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.
citing papers explorer
-
FeynmanBench: Benchmarking Multimodal LLMs on Diagrammatic Physics Reasoning
FeynmanBench is the first benchmark for evaluating multimodal LLMs on diagrammatic reasoning with Feynman diagrams, revealing systematic failures in enforcing physical constraints and global topology.
-
Beyond Accuracy: Evaluating Strategy Diversity in LLM Mathematical Reasoning
Frontier LLMs achieve 95-100% accuracy on AMC/AIME problems but recover far fewer distinct valid strategies than human references, while collectively generating 50 novel strategies.
-
OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving
OptiVerse is a new benchmark spanning neglected optimization domains that shows LLMs suffer sharp accuracy drops on hard problems due to modeling and logic errors, with a Dual-View Auditor Agent proposed to improve performance.
-
Beyond "I Don't Know": Evaluating LLM Self-Awareness in Discriminating Data and Model Uncertainty
Frontier LLMs struggle to discriminate data uncertainty from model uncertainty even when accurate, but a new benchmark and lightweight RL strategy improve attribution without sacrificing answer accuracy.
-
Multi-objective Evolutionary Merging Enables Efficient Reasoning Models
Evo-L2S uses multi-objective evolutionary model merging to produce reasoning models that cut generated chain-of-thought length by over 50% while preserving or improving accuracy on math benchmarks.
-
H\"older Policy Optimisation
HölderPO unifies token aggregation in GRPO via the Hölder mean with dynamic p annealing, reporting 54.9% average math-benchmark accuracy and 93.8% ALFWorld success.
-
Evolutionary Task Discovery: Advancing Reasoning Frontiers via Skill Composition and Complexity Scaling
EvoTD applies crossover for skill composition and parametric mutation for complexity scaling, filtered by a Zone of Proximal Development, to generate tasks that improve LLM reasoning generalization across models.
-
Selective Off-Policy Reference Tuning with Plan Guidance
SORT turns all-wrong prompts into selective learning signals by weighting tokens more predictable under plan guidance from reference solutions, improving over GRPO on reasoning benchmarks especially for weaker models.
-
Process Supervision of Confidence Margin for Calibrated LLM Reasoning
RLCM trains LLMs with a margin-enhanced process reward that widens the gap between correct and incorrect reasoning steps, improving calibration on math, code, logic, and science tasks without hurting accuracy.
-
Dual-Cluster Memory Agent: Resolving Multi-Paradigm Ambiguity in Optimization Problem Solving
DCM-Agent improves LLM performance on multi-paradigm optimization problems by 11-21% via dual-cluster memory construction and dynamic inference guidance.
-
Process Reward Models Meet Planning: Generating Precise and Scalable Datasets for Step-Level Rewards
PDDL planning problems are used to generate about one million precise reasoning steps for training Process Reward Models, and adding this data to existing datasets improves LLM performance on both mathematical and non-mathematical reasoning benchmarks.
-
The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
MEDS improves LLM RL performance by up to 4.13 pass@1 and 4.37 pass@128 points by dynamically penalizing rollouts matching prevalent historical error clusters identified via memory-stored representations and density clustering.
-
Native Parallel Reasoner: Reasoning in Parallelism via Self-Distilled Reinforcement Learning
NPR trains LLMs to reason in parallel via self-distilled RL, delivering up to 24.5% performance gains and 4.6x speedups with 100% genuine parallel execution on reasoning benchmarks.
-
Entropy Ratio Clipping as a Soft Global Constraint for Stable Reinforcement Learning
Entropy Ratio Clipping introduces a global entropy-ratio constraint that stabilizes RL policy updates in LLM post-training beyond local PPO clipping.
-
Process Reinforcement through Implicit Rewards
PRIME enables online process reward model updates in LLM RL using implicit rewards from rollouts and outcome labels, yielding 15.1% average gains on reasoning benchmarks and surpassing a stronger instruct model with 10% of the data.
-
ExpThink: Experience-Guided Reinforcement Learning for Adaptive Chain-of-Thought Compression
ExpThink applies experience-tracked rewards and correct-count normalized advantages in RL to compress CoT reasoning, cutting length up to 77% while raising accuracy and efficiency ratio on math benchmarks.
-
Beyond Benchmarks: MathArena as an Evaluation Platform for Mathematics with LLMs
MathArena is a maintained platform evaluating LLMs across olympiad problems, proofs, research questions, and formal proofs, with GPT-5.5 reaching 98% on 2026 USAMO and 74% on research-level tasks.
-
OGER: A Robust Offline-Guided Exploration Reward for Hybrid Reinforcement Learning
OGER adds an auxiliary exploration reward built from offline trajectories and model entropy to hybrid RL training, yielding gains on math reasoning benchmarks and out-of-domain generalization.
-
Efficient Test-Time Scaling via Temporal Reasoning Aggregation
TRACE aggregates answer consistency and confidence trajectory over multiple reasoning steps to decide when to halt inference, reducing token usage by 25-30% while keeping accuracy within 1-2% of full reasoning.
-
Towards Reasoning Era: A Survey of Long Chain-of-Thought for Reasoning Large Language Models
The paper unifies perspectives on Long CoT in reasoning LLMs by introducing a taxonomy, detailing characteristics of deep reasoning and reflection, and discussing emergence phenomena and future directions.