TSR · The desk
Mathematics · September 2026
Articles in this category in September 2026.
TSR Desk · mathematics · 30 September 2026, 01:00 UTC
COUNTERMEM: World-Model Verified Counter-Factual Memory for Language AgentsTSR Desk · mathematics · 30 September 2026, 01:00 UTC
From Reasoning to Generalization: Knowledge-Augmented LLMs for ARC BenchmarkTSR Desk · mathematics · 29 September 2026, 01:00 UTC
Evaluation is All You Need: Strategic Overclaiming of LLM Reasoning Capabilities ThroughTSR Desk · mathematics · 26 September 2026, 01:00 UTC
Reinforcement Learning with Verifiable Rewards for Small Search AgentsTSR Desk · mathematics · 25 September 2026, 01:00 UTC
Capable yet Parsimonious: Extracting and Characterizing Hidden Chain-of-Thought in FrontierTSR Desk · mathematics · 25 September 2026, 01:00 UTC
You Only Need 2/3 of the Chosen Experts: An Empirical Study of Dynamic Expert Pruning inTSR Desk · mathematics · 24 September 2026, 01:00 UTC
FrontierMath Erd\H{o}sTSR Desk · mathematics · 24 September 2026, 01:00 UTC
VACS: Value-Aligned Compositional Shielding for Multi-Agent ReasoningTSR Desk · mathematics · 23 September 2026, 01:00 UTC
CogGym: Towards Large-Scale Comparative Evaluation of Human and Machine CognitionTSR Desk · mathematics · 15 September 2026, 01:00 UTC
EduFair-Bench: Evaluating Pedagogical Fairness of LLM Tutors Across Student DemographicsTSR Desk · mathematics · 8 September 2026, 01:00 UTC
MABPD: Multi-Agent Bias Probing & Detection via Structured Argument DebateTSR Desk · mathematics · 8 September 2026, 01:00 UTC
GSM8K-V: Can Vision Language Models Solve Grade School Math Word Problems in Visual ContextsTSR Desk · mathematics · 8 September 2026, 01:00 UTC
AxQM: A Textbook-Scale Benchmark for Formal Proof Synthesis in a Library of Finite-DimensionalTSR Desk · mathematics · 4 September 2026, 19:01 UTC
PatchBench: Evaluating AI Agents for Vulnerability PatchingTSR Desk · mathematics · 4 September 2026, 19:01 UTC
Evolving Excellence: Automated Optimization of LLM-based AgentsTSR Desk · mathematics · 4 September 2026, 19:01 UTC
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR