https://evolution.openpressnews.com/timeevo-failure-driven-self-evolution-of-a-time-series-agent OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z TimeEvo: Failure-Driven Self-Evolution of a Time Series Agent https://evolution.openpressnews.com/drsr-learning-set-level-deletion-risk-for-efficient-long-horizon-agents OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z DRSR: Learning Set-Level Deletion Risk for Efficient Long-Horizon Agents https://evolution.openpressnews.com/caveat-towards-robust-computer-use-agents-in-incentive-misaligned-environments OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z CAVEAT: Towards Robust Computer-Use Agents in Incentive-Misaligned Environments https://evolution.openpressnews.com/xlog-a-cuda-native-engine-for-neurosymbolic-integration OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z XLOG: A CUDA-Native Engine for Neurosymbolic Integration https://evolution.openpressnews.com/enhancing-small-language-models-for-power-outage-report-generation-via-minimum-r OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Enhancing Small Language Models for Power Outage Report Generation via Minimum Risk Training https://evolution.openpressnews.com/do-we-need-complex-topology-control-distinct-peer-random-routing-improves-cost-e OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Do We Need Complex Topology Control? Distinct-Peer Random Routing Improves Cost-Efficiency in Sparse Multi-Agent Debate https://evolution.openpressnews.com/provably-complete-generalized-planning-with-llms OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Provably Complete Generalized Planning with LLMs https://evolution.openpressnews.com/policy-as-skill-governed-llm-decision-support-with-evidence-deterministic-contro OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Policy-as-Skill: Governed LLM Decision Support with Evidence, Deterministic Control, and Audit https://evolution.openpressnews.com/propose-don-t-judge-an-anytime-valid-referee-for-llm-agents-that-mine-investment OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Propose, Don't Judge: An Anytime-Valid Referee for LLM Agents That Mine Investment Factors https://evolution.openpressnews.com/math-reasoning-in-llms-is-organized-by-approach-not-topic OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Math Reasoning in LLMs is Organized by Approach, Not Topic https://evolution.openpressnews.com/are-stated-reasoning-steps-causally-load-bearing OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Are Stated Reasoning Steps Causally Load-Bearing? https://evolution.openpressnews.com/training-intelligent-voice-assistant-wakeup-with-controllable-synthetic-conversa OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Training Intelligent Voice Assistant Wakeup with Controllable Synthetic Conversations https://evolution.openpressnews.com/reinforcement-learning-with-decomposed-subtasks OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Reinforcement Learning with Decomposed Subtasks https://evolution.openpressnews.com/same-evidence-different-judgments-evidence-noncommutative-in-vision-speech-text- OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Same evidence, different judgments: Evidence noncommutative in vision/speech-text conflicts https://evolution.openpressnews.com/escaping-python-dependency-hell-a-hybrid-replay-and-repair-pipeline-for-python-d OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Escaping Python Dependency Hell: A Hybrid Replay-and-Repair Pipeline for Python Dependency Resolution https://evolution.openpressnews.com/which-objectives-need-a-dial-predicting-objective-conflict-and-covering-trade-of OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Which Objectives Need a Dial? Predicting Objective Conflict and Covering Trade-offs in Steerable Pluralistic Alignment https://evolution.openpressnews.com/building-socio-affective-artificial-intelligence-for-interactive-multi-agent-sim OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Building Socio-Affective Artificial Intelligence for Interactive Multi-Agent Simulations https://evolution.openpressnews.com/twincheck-evidence-grounded-negative-twin-verification-for-stateful-tool-agents OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z TwinCheck: Evidence-Grounded Negative-Twin Verification for Stateful Tool Agents https://evolution.openpressnews.com/harness-as-a-language-a-minimalist-agent-framework-with-maximal-expressivity OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Harness as a Language: A Minimalist Agent Framework With Maximal Expressivity https://evolution.openpressnews.com/silent-failures-in-agent-tool-interaction-an-audit-of-tooluniverse OpenPress AI Evolution Intelligenceen 2026-09-24T04:00:00.000Z Silent Failures in Agent-Tool Interaction: An Audit of ToolUniverse