KCSAT-ML benchmark supplies human error rates for math problems and DRG metric exposes that model accuracy collapses on high-human-error items while test-time scaling shows non-monotonic gains and alignment failures.
hub Canonical reference
Forest-of-thought: Scaling test-time compute for enhancing llm reasoning.ArXiv, abs/2412.09078, Dec 2412
Canonical reference. 83% of citing Pith papers cite this work as background.
14
Pith papers citing it
1
external citations · external index
Background
83% of classified citations
hub tools
citation-role summary
background 5
method 1
citation-polarity summary
representative citing papers
TTRL-CoCoV is a confidence-conditioned test-time RL framework that selectively applies verification to address pseudo-label errors and diversity collapse, yielding +9.8% Pass@1 and +18.7% Pass@16 gains over prior TTRL on reasoning benchmarks.
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
DIRECT is a multimodal-context router that allocates test-time compute across chain-of-thought depth, model size, and memory history for VLM embodied planners, improving the success-cost Pareto frontier and matching stronger models at up to 65% lower latency on benchmarks and a physical Franka arm.
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
Hive is a multi-agent infrastructure with a logits cache for reducing cross-path redundancy in sampling and agent-aware scheduling for better compute and KV-cache allocation, shown to deliver 1.11x-1.76x speedups and 33%-51% lower hotspot miss rates.
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.
Curtailing diversity in candidate pools for test-time scaling increases unsafe LLM outputs, as demonstrated by a reference-guided reduction protocol that evades standard safety classifiers across open and closed models.
DeepSearch embeds MCTS into RLVR training with global frontier selection, entropy guidance, and adaptive replay to achieve 62.95% average accuracy on math reasoning benchmarks while using 5.7x fewer GPU hours than extended training.
A disagreement-based router that decides per math problem whether to accept, majority-vote, or rewrite improves accuracy by 3–7% with fewer samples than fixed test-time scaling methods.
Thinking LLMs achieve ~10 percentage points higher accuracy than non-thinking ones on RewardBench with under 2x compute overhead, outperforming augmentation strategies that cost over 8x more while also showing better bias robustness.
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.
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.
citing papers explorer
-
KCSAT-ML: Probing Reasoning Models with Nationwide-Cohort Human Difficulty
KCSAT-ML benchmark supplies human error rates for math problems and DRG metric exposes that model accuracy collapses on high-human-error items while test-time scaling shows non-monotonic gains and alignment failures.
-
Exploiting Verification-Generation Gap: Test-Time Reinforcement Learning with Confidence-Conditioned Verification
TTRL-CoCoV is a confidence-conditioned test-time RL framework that selectively applies verification to address pseudo-label errors and diversity collapse, yielding +9.8% Pass@1 and +18.7% Pass@16 gains over prior TTRL on reasoning benchmarks.
-
MetaPS: Adaptive Programmatic Strategy Selection for Market Agents
MetaPS trains models via simulation rollouts to select from programmatic strategy libraries for market agents, yielding better performance than fixed or direct LLM baselines across model sizes.
-
DIRECT: When and Where Should You Allocate Test-Time Compute in Embodied Planners?
DIRECT is a multimodal-context router that allocates test-time compute across chain-of-thought depth, model size, and memory history for VLM embodied planners, improving the success-cost Pareto frontier and matching stronger models at up to 65% lower latency on benchmarks and a physical Franka arm.
-
Confidence-Aware Alignment Makes Reasoning LLMs More Reliable
CASPO trains LLMs via iterative direct preference optimization so that token-level confidence tracks step-wise correctness, then applies Confidence-aware Thought pruning at inference to improve both reliability and speed on reasoning benchmarks.
-
Hive: A Multi-Agent Infrastructure for Algorithm- and Task-Level Scaling
Hive is a multi-agent infrastructure with a logits cache for reducing cross-path redundancy in sampling and agent-aware scheduling for better compute and KV-cache allocation, shown to deliver 1.11x-1.76x speedups and 33%-51% lower hotspot miss rates.
-
TDA-RC: Task-Driven Alignment for Knowledge-Based Reasoning Chains in Large Language Models
TDA-RC embeds topological patterns from multi-round reasoning into CoT via persistent homology and a repair agent, yielding better accuracy-efficiency trade-offs than ToT or GoT on tested datasets.
-
Less Diverse, Less Safe: The Indirect But Pervasive Risk of Test-Time Scaling in Large Language Models
Curtailing diversity in candidate pools for test-time scaling increases unsafe LLM outputs, as demonstrated by a reference-guided reduction protocol that evades standard safety classifiers across open and closed models.
-
DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
DeepSearch embeds MCTS into RLVR training with global frontier selection, entropy guidance, and adaptive replay to achieve 62.95% average accuracy on math reasoning benchmarks while using 5.7x fewer GPU hours than extended training.
-
When to Vote, When to Rewrite: Disagreement-Guided Strategy Routing for Test-Time Scaling
A disagreement-based router that decides per math problem whether to accept, majority-vote, or rewrite improves accuracy by 3–7% with fewer samples than fixed test-time scaling methods.
-
Explicit Reasoning Makes Better Judges: A Systematic Study on Accuracy, Efficiency, and Robustness
Thinking LLMs achieve ~10 percentage points higher accuracy than non-thinking ones on RewardBench with under 2x compute overhead, outperforming augmentation strategies that cost over 8x more while also showing better bias robustness.
-
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.
-
A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence
The paper delivers the first systematic review of self-evolving agents, structured around what components evolve, when adaptation occurs, and how it is implemented.
-
From System 1 to System 2: A Survey of Reasoning Large Language Models
The survey organizes the shift of LLMs toward deliberate System 2 reasoning, covering model construction techniques, performance on math and coding benchmarks, and future research directions.