When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable and RLVR-optimal.
hub
Science , volume=
18 Pith papers cite this work. Polarity classification is still indexing.
18
Pith papers citing it
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
GAMBLe decomposes ADRS into four parameters and an effective landscape, with experiments on 760+ runs across NP-hard problems showing no universal best generator or mechanism and potential gains of 13-67% from component choice.
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
AgentLens reveals 10.7% of passing SWE-agent trajectories exhibit Lucky Pass behaviors and introduces a process-level evaluation framework with a new annotated dataset of 1,815 trajectories.
Cross-modal agreement between chain-of-thought and program-of-thought reasoning enables self-consistency with only two LLM samples, reducing sampling cost by 9.3x while improving accuracy.
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
Viverra generates C code from text descriptions together with assertions that are verified by model checkers, and a user study with over 400 participants shows the verified assertions improve code comprehension.
PaT defers planning until after failed trials in LLM code generation, enabling heterogeneous cheap-plus-powerful model setups that match large-model performance at roughly 69% lower cost.
Programmatic context augmentation lets LLM-based symbolic regression perform code-driven data analysis during search, yielding superior efficiency and accuracy over baselines on LLM-SRBench.
APPS approximates power targets p(x)^alpha via parallel particle propagation with proposal-corrected reweighting and future-value-guided selection at block boundaries, improving accuracy-runtime trade-offs in training-free decoding.
RAGP models prompt compression as redundancy-aware pruning on a multiplex graph using Lévy walks, achieving 49.3 average on LongBench at 4x compression versus 48.8 for LongLLMLingua at 3x.
FUSE ensembles verifiers unsupervisedly by controlling their conditional dependencies to improve spectral ensembling algorithms, matching or exceeding semi-supervised baselines on benchmarks including GPQA Diamond and Humanity's Last Exam.
SOCIA-EVO generates statistically consistent simulators by separating structural refinement from parameter calibration via bi-level optimization and falsifying strategies through execution feedback in a Bayesian-weighted playbook.
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
Self-Debugging teaches LLMs to identify and fix their own code errors through rubber-duck-style natural language explanations and execution feedback, delivering 2-12% gains over baselines on Spider, TransCoder, and MBPP.
Pass-rate rewards in critic-free RL for code generation fail to outperform binary rewards because partial-pass solutions induce conflicting gradient directions that do not consistently favor full correctness.
Longitudinal poll data from 471 students in AI courses shows a shift toward preferring human intelligence, reaching 65% in technical courses and 90% in design courses by 2026.
citing papers explorer
-
When Does In-Context Search Help? A Sampling-Complexity Theory of Reflection-Driven Reasoning
When reflections localize early errors, in-context search solves exp-small pass-rate problems with poly sequential attempts; otherwise it offers no asymptotic gain over parallel sampling, and the update is learnable and RLVR-optimal.
-
Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems
GAMBLe decomposes ADRS into four parameters and an effective landscape, with experiments on 760+ runs across NP-hard problems showing no universal best generator or mechanism and potential gains of 13-67% from component choice.
-
BOOKMARKS: Efficient Active Storyline Memory for Role-playing
BOOKMARKS introduces searchable bookmarks as reusable answers to storyline questions, enabling active initialization and passive synchronization for more consistent role-playing agent memory than recurrent summarization.
-
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
AgentLens reveals 10.7% of passing SWE-agent trajectories exhibit Lucky Pass behaviors and introduces a process-level evaluation framework with a new annotated dataset of 1,815 trajectories.
-
Self-Consistency from Only Two Samples: CoT-PoT Ensembling for Efficient LLM Reasoning
Cross-modal agreement between chain-of-thought and program-of-thought reasoning enables self-consistency with only two LLM samples, reducing sampling cost by 9.3x while improving accuracy.
-
Rethinking Code Performance Benchmarks for LLMs
Re-evaluating four LLM code-efficiency benchmarks with 30-run statistical testing shows 93.89% of 'performant' implementations are indistinguishable from baselines; a multi-agent test-generation framework reveals hidden significant improvements in ~24% of previously non-significant tasks.
-
Viverra: Text-to-Code with Guarantees
Viverra generates C code from text descriptions together with assertions that are verified by model checkers, and a user study with over 400 participants shows the verified assertions improve code comprehension.
-
PaT: Planning-after-Trial for Efficient Test-Time Code Generation
PaT defers planning until after failed trials in LLM code generation, enabling heterogeneous cheap-plus-powerful model setups that match large-model performance at roughly 69% lower cost.
-
Programmatic Context Augmentation for LLM-based Symbolic Regression
Programmatic context augmentation lets LLM-based symbolic regression perform code-driven data analysis during search, yielding superior efficiency and accuracy over baselines on LLM-SRBench.
-
The Model Knows, the Decoder Finds: Future Value Guided Particle Power Sampling
APPS approximates power targets p(x)^alpha via parallel particle propagation with proposal-corrected reweighting and future-value-guided selection at block boundaries, improving accuracy-runtime trade-offs in training-free decoding.
-
Mapping Text to Multiplex Graph: Prompt Compression as L\'evy Walk-Guided Graph Pruning
RAGP models prompt compression as redundancy-aware pruning on a multiplex graph using Lévy walks, achieving 49.3 average on LongBench at 4x compression versus 48.8 for LongLLMLingua at 3x.
-
FUSE: Ensembling Verifiers with Zero Labeled Data
FUSE ensembles verifiers unsupervisedly by controlling their conditional dependencies to improve spectral ensembling algorithms, matching or exceeding semi-supervised baselines on benchmarks including GPQA Diamond and Humanity's Last Exam.
-
SOCIA-EVO: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization
SOCIA-EVO generates statistically consistent simulators by separating structural refinement from parameter calibration via bi-level optimization and falsifying strategies through execution feedback in a Bayesian-weighted playbook.
-
ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolution
ShinkaEvolve improves sample efficiency in LLM-driven program evolution via parent sampling, code novelty rejection-sampling, and bandit LLM ensemble selection, achieving new SOTA circle packing with 150 samples and gains on math reasoning and competitive programming tasks.
-
OS-ATLAS: A Foundation Action Model for Generalist GUI Agents
OS-Atlas, trained on the largest open-source cross-platform GUI grounding corpus of 13 million elements, outperforms prior open-source models on six benchmarks across mobile, desktop, and web platforms.
-
Teaching Large Language Models to Self-Debug
Self-Debugging teaches LLMs to identify and fix their own code errors through rubber-duck-style natural language explanations and execution feedback, delivering 2-12% gains over baselines on Spider, TransCoder, and MBPP.
-
Exploring Pass-Rate Reward in Reinforcement Learning for Code Generation
Pass-rate rewards in critic-free RL for code generation fail to outperform binary rewards because partial-pass solutions induce conflicting gradient directions that do not consistently favor full correctness.
-
Evidence of a Cognitive Shift in AI Education: How Students Are Rethinking Human Intelligence?
Longitudinal poll data from 471 students in AI courses shows a shift toward preferring human intelligence, reaching 65% in technical courses and 90% in design courses by 2026.