{"total":39,"rows":[{"id":"2211.14275","title":"Solving math word problems with process- and outcome-based feedback","created":"2022-11-25","cited_by_count":901,"area":"lr"},{"id":"2501.19306","title":"SETS: Leveraging Self-Verification and Self-Correction for Improved Test-Time Scaling","created":"2025-01-31","cited_by_count":54,"area":"lr"},{"id":"2609.26550","title":"JEV-as-a-Judge: Accept When Confident, Escalate When Unsure","created":"2026-09-22","cited_by_count":30,"area":"lr"},{"id":"2502.13962","title":"Is That Your Final Answer? Test-Time Scaling Improves Selective Question Answering","created":"2025-02-19","cited_by_count":17,"area":"lr"},{"id":"2609.31142","title":"JevAdvBench: A Benchmark and Black-Box Attacks for Reinforcement Learning for Calibrated Decisions Models","created":"2026-09-25","cited_by_count":10,"area":"lr"},{"id":"2604.14853","title":"Adaptive Test-Time Compute Allocation for Reasoning LLMs via Constrained Policy Optimization","created":"2026-04-16","cited_by_count":9,"area":"lr"},{"id":"2602.17633","title":"When to Trust the Cheap Check: Weak and Strong Verification for Reasoning","created":"2026-02-19","cited_by_count":7,"area":"lr"},{"id":"2605.04039","title":"Safety and accuracy follow different scaling laws in clinical large language models","created":"2026-05-05","cited_by_count":6,"area":"lr"},{"id":"2505.09591","title":"Variational Visual Question Answering for Uncertainty-Aware Selective Prediction","created":"2025-05-14","cited_by_count":5,"area":"lr"},{"id":"2601.11644","title":"Predicting When to Trust Vision-Language Models for Spatial Reasoning","created":"2026-01-14","cited_by_count":5,"area":"lr"},{"id":"2507.09751","title":"Sound and Complete Neurosymbolic Reasoning with LLM-Grounded Interpretations","created":"2025-07-13","cited_by_count":4,"area":"lr"},{"id":"2604.19444","title":"Unsupervised Confidence Calibration for Reasoning LLMs from a Single Generation","created":"2026-04-21","cited_by_count":3,"area":"lr"},{"id":"2606.04402","title":"Not All Errors Are Equal: Consequence-Aware Reasoning Compute Allocation","created":"2026-06-03","cited_by_count":3,"area":"lr"},{"id":"2605.19228","title":"Diagnosing Multi-step Reasoning Failures in Black-box LLMs via Stepwise Confidence Attribution","created":"2026-05-19","cited_by_count":2,"area":"lr"},{"id":"2605.30557","title":"Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?","created":"2026-05-28","cited_by_count":2,"area":"lr"},{"id":"2607.06799","title":"What Predicts Correctness in Text-to-SQL? A Selective-Prediction Study","created":"2026-07-07","cited_by_count":2,"area":"lr"},{"id":"2607.08065","title":"When LLMs Agree, Are They Right? Auditing Self-Consistency and Cross-Model Agreement as Confidence Signals","created":"2026-07-09","cited_by_count":2,"area":"lr"},{"id":"2511.05804","title":"Catching Contamination Before Generation: Spectral Kill Switches for Agents","created":"2025-11-08","cited_by_count":1,"area":"lr"},{"id":"2601.19931","title":"CascadeMind at SemEval-2026 Task 4: A Hybrid Neuro-Symbolic Cascade for Narrative Similarity","created":"2026-01-12","cited_by_count":1,"area":"lr"},{"id":"2602.08520","title":"Reinforcement Inference: Leveraging Uncertainty for Self-Correcting Language Model Reasoning","created":"2026-02-09","cited_by_count":1,"area":"lr"},{"id":"2605.14098","title":"Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning","created":"2026-05-13","cited_by_count":1,"area":"lr"},{"id":"2606.24281","title":"CALIBER: Calibrating Confidence Before and After Reasoning in Language Models","created":"2026-06-23","cited_by_count":1,"area":"lr"},{"id":"2606.29654","title":"Budgeted Act-or-Defer Multi-Agent LLM Deliberation with Local Reliability Bounds","created":"2026-06-28","cited_by_count":1,"area":"lr"},{"id":"2607.13753","title":"Post-Training Shifts Confidence: A Three-Stage Analysis of How SFT, RL, and OPD Shape CoT Calibration","created":"2026-07-15","cited_by_count":1,"area":"lr"},{"id":"2610.09683","title":"System Switch: When Should a Fast Decision Model Stop and Think?","created":"2026-10-07","cited_by_count":1,"area":"lr"},{"id":"2507.14406","title":"Fail Fast, or Ask: Mitigating the Deficiencies of Reasoning LLMs with Human-in-the-Loop Systems Engineering","created":"2025-07-18","cited_by_count":0,"area":"lr"},{"id":"2604.11996","title":"Filtered Reasoning Score: Evaluating Reasoning Quality on a Model's Most-Confident Traces","created":"2026-04-13","cited_by_count":0,"area":"lr"},{"id":"2605.30660","title":"BOKBO (Best of K Bad Options): Calibrated Abstention for VLA Policies","created":"2026-05-28","cited_by_count":0,"area":"lr"},{"id":"2606.13649","title":"Operadic consistency: a label-free signal for compositional reasoning failures in LLMs","created":"2026-06-11","cited_by_count":0,"area":"lr"},{"id":"2606.19812","title":"Human-on-the-Loop Orchestration for AI-Assisted Legal Discovery","created":"2026-06-18","cited_by_count":0,"area":"lr"},{"id":"2606.21083","title":"Coherence Under Commitment: Probing Generalization and Vacuous Memorization in LLM Logical Reasoning","created":"2026-06-19","cited_by_count":0,"area":"lr"},{"id":"2608.10441","title":"Detecting an Effect Is Not Learning to Act on It: A Reward-SNR Floor for LLM Acquisition Agents","created":"2026-08-11","cited_by_count":0,"area":"lr"},{"id":"2608.18833","title":"EVADE: Evidence-Verified Agentic Diagnosis with Escape","created":"2026-08-19","cited_by_count":0,"area":"lr"},{"id":"2608.28402","title":"VERA-8B: Evidence-Grounded Audit Risk Reasoning from SEC Filings","created":"2026-08-28","cited_by_count":0,"area":"lr"},{"id":"2609.06403","title":"From Concentration to Differentiation and Back: Routing Effective Rank in MoE Reasoning Cohorts","created":"2026-09-06","cited_by_count":0,"area":"lr"},{"id":"2609.17686","title":"The Missing \"I Don't Know\": Why Three Reasoning-Reliability Findings Converge on Calibrated Abstention","created":"2026-09-15","cited_by_count":0,"area":"lr"},{"id":"2609.34857","title":"Beyond Verbalized Confidence: Calibrating Reasoners with Differentiable Readouts","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.38850","title":"OpenJev-RLCD: A Working RLCD Implementation","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.14403","title":"VisualCoding: Learning Executable Skills for Reliable Visual Reasoning","created":"2026-10-09","cited_by_count":0,"area":"lr"}],"next_cursor":null}