01. Charts as Epistemic Actions for Experience-Driven Agentic Data Analysis

85% worth reading · novelty 1.9/3 · new method · cs.AI

02. Conflicted Records: Typed Adversarial Contracts for Auditable LLM Output Quality Enforcement

86% worth reading · novelty 1.9/3 · new method · cs.MA

03. The End of Consensus Research?

79% worth reading · novelty 2.2/3 · new method · cs.AI

04. What the Author Wrote, What the Agent Reads: Silent Cue Loss in Enterprise Document Ingestion

82% worth reading · novelty 1.9/3 · benchmark/eval · cs.CL

05. Agent Behavior Maps: Locating Agents by What They Would Do, Without Running Them

80% worth reading · novelty 1.9/3 · new method · cs.CL

06. Remembering Through Change: Provenance-Preserving Hypergraph Memory for Multimodal Agents

81% worth reading · novelty 1.8/3 · new method · cs.CL

07. Fig: Automated Multiagent Behavior Elicitor

80% worth reading · novelty 1.9/3 · new method · cs.MA

08. OACap: Caption-Guided Active Observation for Detailed Video Captioning

82% worth reading · novelty 1.7/3 · new method · cs.MA

09. Environment Duels: A Microcosm of LLM Co-Evolution

79% worth reading · novelty 1.9/3 · benchmark/eval · cs.AI

10. Credit Where Credit Is Due: Contrastive Attribution Topology Search for Multi-Agent Systems

81% worth reading · novelty 1.8/3 · new method · cs.MA

11. LongZero: Enhancing Long-Context Reasoning in LLMs from Zero Data

77% worth reading · novelty 1.9/3 · new method · cs.CL

12. Did the Problem Actually Get Harder? Testing LLMs on Paired P and NP-Complete Problems Hardened by Adversarial Multi-Agent Rewriting

75% worth reading · novelty 1.9/3 · benchmark/eval · cs.CL

13. ToM2Vec: Continuous Theory-of-Mind Tokens for Multi-Agent Coordination

75% worth reading · novelty 1.9/3 · new method · cs.MA

14. Quant-Arena: Benchmarking LLM Agents for Quantitative Trading Research

76% worth reading · novelty 1.7/3 · benchmark/eval · cs.AI

15. SWE-DIVE: Multi-Turn Coding Agent Evaluation with Dynamic User Simulation

76% worth reading · novelty 1.4/3 · benchmark/eval · cs.AI

16. Multimodal Embodied Agents: A Unified Capability-centric Perspective from Computer-Use to Robot-Use

72% worth reading · novelty 1.7/3 · survey/position · cs.AI

17. Parallel AI Agent Collaboration as Graph-Structured Distributed Block Optimization

69% worth reading · novelty 1.9/3 · new method · cs.AI

18. The Butterfly Effect in LLM Social Simulations: From Architecture Sensitivity to Robustness Audits

70% worth reading · novelty 1.8/3 · benchmark/eval · cs.MA

19. HiddenLens: A Multi-Layer LLM Framework for Detecting and Resolving Hidden Assumptions in Software Requirements

68% worth reading · novelty 1.9/3 · new method · cs.CL

20. Commit or Abstain? System One Decision Models, LLMs, and Missing Legal Authority

72% worth reading · novelty 1.6/3 · benchmark/eval · cs.CL