DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
hub Canonical reference
Large language models are zero-shot reasoners.Advances in neural information processing systems, 35:22199–22213
Canonical reference. 83% of citing Pith papers cite this work as background.
15
Pith papers citing it
Background
83% of classified citations
hub tools
citation-role summary
background 5
method 1
citation-polarity summary
representative citing papers
CAPS is a four-stage inference-only cascade that adapts how much of each solution the verifier sees and how comparisons are distributed, halving per-candidate verifier tokens while outperforming uniform pairwise verification on most benchmarks.
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
MAP improves LLM agent reasoning by constructing a structured cognitive map of the environment before task execution, yielding performance gains on benchmarks like ARC-AGI-3 and superior training data via the new MAP-2K dataset.
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.
RIS improves MLLM latent visual reasoning by retrieving spatial-semantic evidence, integrating it via attention bottlenecks, and synthesizing it with language transition tokens, yielding gains on V*, HRBench, MMVP, and BLINK benchmarks.
RALP learns string-based chain-of-thought prompts as scoring functions for knowledge graph triples using Bayesian optimization from fewer than 30 examples, improving link prediction MRR by over 5% and achieving over 88% Jaccard similarity on complex OWL reasoning tasks.
HCP-MAD reduces token costs in multi-agent debates by using heterogeneous consensus verification, adaptive pair-agent stopping, and escalated collective voting based on task complexity signals.
A new counterfactual multi-agent framework improves LLM diagnostic accuracy by quantifying confidence shifts from edited clinical findings and guiding specialist discussions.
LLM syntax accuracy for LAMMPS scripts improved to 91% parser pass rate, yet only 1/80 scripts were scientifically correct on the hardest prompt; an agentic verification skill raised success to 5/6.
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
LRMs exhibit complete accuracy collapse beyond certain puzzle complexities, with reasoning effort rising then declining, outperforming standard LLMs only on medium-complexity tasks.
SafeLens presents a fast-and-slow video guardrail framework that filters the SafeWatch dataset to 2.4% and adds Chain-of-Thought traces to achieve state-of-the-art moderation performance at reduced inference cost.
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
EMS reduces the average number of agents invoked for majority voting by 32% via reliability-aware prioritization and early stopping on six benchmarks.
citing papers explorer
-
DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Driving
DriveSpatial benchmark shows the best of 15 VLMs trails humans by 28.4 points on spatiotemporal driving tasks, with cognitive scene construction as the main failure mode.
-
CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning
CAPS is a four-stage inference-only cascade that adapts how much of each solution the verifier sees and how comparisons are distributed, halving per-candidate verifier tokens while outperforming uniform pairwise verification on most benchmarks.
-
Query-Conditioned Test-Time Self-Training for Large Language Models
QueST adapts LLMs at test time by generating query-specific problem-solution pairs for self-supervised fine-tuning, improving reasoning performance without external data.
-
MAP: A Map-then-Act Paradigm for Long-Horizon Interactive Agent Reasoning
MAP improves LLM agent reasoning by constructing a structured cognitive map of the environment before task execution, yielding performance gains on benchmarks like ARC-AGI-3 and superior training data via the new MAP-2K dataset.
-
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.
-
Retrieve, Integrate, and Synthesize: Spatial-Semantic Grounded Latent Visual Reasoning
RIS improves MLLM latent visual reasoning by retrieving spatial-semantic evidence, integrating it via attention bottlenecks, and synthesizing it with language transition tokens, yielding gains on V*, HRBench, MMVP, and BLINK benchmarks.
-
Learning Chain Of Thoughts Prompts for Predicting Entities, Relations, and even Literals on Knowledge Graphs
RALP learns string-based chain-of-thought prompts as scoring functions for knowledge graph triples using Bayesian optimization from fewer than 30 examples, improving link prediction MRR by over 5% and achieving over 88% Jaccard similarity on complex OWL reasoning tasks.
-
Heterogeneous Consensus-Progressive Reasoning for Efficient Multi-Agent Debate
HCP-MAD reduces token costs in multi-agent debates by using heterogeneous consensus verification, adaptive pair-agent stopping, and escalated collective voting based on task complexity signals.
-
Improving Clinical Diagnosis with Counterfactual Multi-Agent Reasoning
A new counterfactual multi-agent framework improves LLM diagnostic accuracy by quantifying confidence shifts from edited clinical findings and guiding specialist discussions.
-
Evaluating LLM-generated code for domain-specific languages: molecular dynamics with LAMMPS
LLM syntax accuracy for LAMMPS scripts improved to 91% parser pass rate, yet only 1/80 scripts were scientifically correct on the hardest prompt; an agentic verification skill raised success to 5/6.
-
Self-Supervised Bootstrapping of Action-Predictive Embodied Reasoning
R&B-EnCoRe uses self-supervised importance-weighted variational inference to distill action-predictive reasoning datasets that improve VLA performance on manipulation, navigation, and driving tasks without external verifiers.
-
The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
LRMs exhibit complete accuracy collapse beyond certain puzzle complexities, with reasoning effort rising then declining, outperforming standard LLMs only on medium-complexity tasks.
-
SafeLens: Deliberate and Efficient Video Guardrails with Fast-and-Slow Screening
SafeLens presents a fast-and-slow video guardrail framework that filters the SafeWatch dataset to 2.4% and adds Chain-of-Thought traces to achieve state-of-the-art moderation performance at reduced inference cost.
-
Act Wisely: Cultivating Meta-Cognitive Tool Use in Agentic Multimodal Models
HDPO reframes tool efficiency as a conditional objective within accurate trajectories, enabling Metis to reduce tool invocations by orders of magnitude while raising reasoning accuracy.
-
EMS: Multi-Agent Voting via Efficient Majority-then-Stopping
EMS reduces the average number of agents invoked for majority voting by 32% via reliability-aware prioritization and early stopping on six benchmarks.