AI Agent Papers2026
Evaluates how long-term memory in LLM agents amplifies sycophantic behavior and when memory should or should not influence decisions. Provides five targeted tasks, 1,550 standardized samples, an evaluation pipeline, and baseline adapters to test memory use, conflicts, scope, updates, and personalization.
Predicts per-request MoE expert footprints from prefill activations and routes decode requests to workers that maximize expert-locality, lowering decode latency by combining offline K-means partitioning with online locality-band routing and a KV-block–coindexed signature cache.
Compiles natural-language function specifications into compact, locally-executable neural programs (PAW) that run on a small frozen interpreter; a 4B compiler emits LoRA adapters for a 0.6B runtime to provide offline, low-memory fuzzy text functions.
AI Agent Papers2026
Introduces a bounded-memory, typed-retrieval contract for long-horizon LLM agents and evaluates it in Slay the Spire 2 — assembling per-decision prompts from five typed slots rather than appending raw transcripts. Key outputs include ablationable memory layers, 298 labeled trajectories, and reproducible analysis scripts.
AI Model2026
A 1B-parameter 'Thinking' language model fine-tuned on Fable 5 to improve coding and instruction-following; supports chain-of-thought style outputs, XML tool-call format, and up to 128K-token context, with GGUF builds for single-GPU local deployment.
AI Dataset2026
Converts long or messy model reasoning traces into concise, user-facing summaries with optional metadata. 61K cleaned English samples in JSON format, Apache-2.0 licensed, created to train and evaluate reasoning-summarization models and to present safe, readable explanations instead of raw chain-of-thought.
AI Dataset2026
Provides labeled prompts with full-reference answers (including chain-of-thought and code blocks) and per-example metadata to train edge routing/orchestrator models that decide whether to handle inputs locally or route them to larger models. Includes complexity scores, coding/math flags, routing justifications, and an automated override rule; suited for fine-tuning small models (50M–1.5B) for edge deployment.
Transfers RL-induced policy shifts from a smaller 'weak' teacher to a stronger target by using the teacher's post-/pre-RL log-ratio as a dense implicit reward applied on the student's on-policy states. Enables reuse of RL supervision without running RL rollouts on the target, improving sample/time efficiency.
AI Dataset2026
Structured dataset of internship listings combined with content-performance (SEO) metrics, provided as tabular and textual fields for data-warehouse analysis. Useful for building search/ranking features, training NLP models on internship-related queries, or performing analytics on content performance.
Introduces KronQ, a post-training quantization framework that incorporates gradient covariance via a Kronecker‑factored Hessian to guide input/output weight rotations and sensitivity-driven mixed-precision allocation. Demonstrates stable 2-bit weight-only quantization on LLaMA-3-70B (7.93 PPL).
AI Dataset2026
Provides ~5M model-generated reasoning chains (within 5k sequence length) with structured fields for supervised fine-tuning, reasoning distillation, and instruction tuning. Includes separate fields for prompt, reasoning trace, final answer and a ChatML view; streaming access recommended for large-scale use.
Provides IdeaGene-Bench, a dataset and evaluation suite for scientific-lineage reasoning and lineage-grounded idea generation, representing papers as minimal, typed Idea Genome objects and GenomeDiffs that record inheritance, mutation, loss, import and novel insertion. Includes 1,961 lineage traces, IG-Exam (42 task types) and IG-Arena with a Population-Evolution Score for generation.