Papers

• FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents (2026)
  Yufeng Wang
  2.00
• Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability (2026)
  Sizhe Zhou et al.
  2.00
• RepoRescue: An Empirical Study of LLM Agents on Whole-Repository Compatibility Rescue (2026)
  Zhihao Lin et al.
  2.00
• WorldDirector: Building Controllable World Simulators with Persistent Dynamic Memory (2026)
  Hanlin Wang et al.
  2.00
• Managing Procedural Memory in LLM Agents: Control, Adaptation, and Evaluation (2026)
  Julia Belikova et al.
  1.94
• TheoremGraph: Bridging Formal and Informal Mathematics (2026)
  Simon Kurgan et al.
  1.94
• Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement (2026)
  Igor Itkin
  1.94
• Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math Reasoning (2026)
  Sangmook Lee et al.
  1.94
• QVal: Cheaply Evaluating Dense Supervision Signals for Long-Horizon LLM Agents (2026)
  Sergio Hernández-Gutiérrez et al.
  1.94
• Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction (2026)
  Mingzhe Du et al.
  1.94
• Safety Testing LLM Agents at Scale: From Risk Discovery to Evidence-Grounded Verification (2026)
  Yunhao Feng et al.
  1.94
• Unified Audio Intelligence Without Regressing on Text Intelligence (2026)
  Zhifeng Kong et al.
  1.94
• TRACE: Business Rule-Grounded Reasoning Curriculum for Knowledge-Preserving Parametric Tool Retrieval in Enterprise LLMs (2026)
  Sai Shruthi Sistla et al.
  1.94
• Novel Claim or Déjà Vu? Rethinking "Contamination-Free'' Dynamic Evaluation for Multimodal Automated Fact-Checking (2026)
  Haorui He et al.
  1.94
• A Frozen 12B Beats Frontier Models on Verified Work: 100% Accuracy, 0 Tokens, Bit-Exact, Forever (2026)
  Sietse Schelpe
  1.94
• GORGO: Online Tuning for Cross-Region Network-Aware LLM Serving (2026)
  Alessio Ricci Toniolo et al.
  1.72