Tracked topic
…Contextual Capability Calibration for Multi-Agent Delegation (2026) TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration (2026) Orchard: An Open-Source Agentic Modeling Framework (2026) Towards Long-horizon Agentic…
…We evaluate the Specification on a prototype benchmark of held-out behavioral predictions scored by a calibrated 5-judge LLM panel. We test it independently and in composition with a range of…
…Simple Calibrated Test-Time Ranking (2026) From Tokens to Steps: Verification-Aware Speculative Decoding for Efficient Multi-Step Reasoning (2026) Process Reward Agents for Steering Knowledge-Intensive Reasoning (2026) GCoT-Decoding: Unlocking…
…while still subsuming generic quality criteria ✅, and its reliability masking effectively identifies and suppresses poorly-calibrated scoring dimensions 🛡️. Get this paper in your agent: hf papers read 2605.30288 Don't…
…Flexible Speculative Decoding via Attention Tuning and Bonus-Guided Calibration (2026) Draft-OPD: On-Policy Distillation for Speculative Draft Models (2026) PARD-2: Target-Aligned Parallel Draft Model for Dual-Mode Speculative…
…Our construction pipeline rejects 70.3% of LLM -generated candidates at a search-based external-verification stage, calibrating how unreliable industrial QA remains after LLM -only filtering.Our evaluation decouples raw correctness…
…Improving Text-Only Calibration of Vision Language Models (2026) From Pixels to Words -- Towards Native One-Vision Models at Scale (2026) UniVLR: Unifying Text and Vision in Visual Latent Reasoning for Multimodal…
…filtered claims" stays partially falsifiable in the wild, and the complete-oracle domains become the calibration set: they tell you how often grown-evidence actually converts into grown-relevant-coverage, which is…
…did you try any calibration mechanism to anchor rubrics across stages so credit signals stay aligned with the intended semantics rather than chasing emergent artifacts? an ablation removing the rubric memory would…
…Orchestrating Safety-Aware Visual Narratives via Multi-Agent Cognitive Calibration (2026) Think in Strokes, Not Pixels: Process-Driven Image Generation via Interleaved Reasoning (2026) Affordance Agent Harness: Verification-Gated Skill Orchestration (2026…