MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
hub
RULER: What's the Real Context Size of Your Long-Context Language Models?
59 Pith papers cite this work. Polarity classification is still indexing.
59
Pith papers citing it
abstract
The needle-in-a-haystack (NIAH) test, which examines the ability to retrieve a piece of information (the "needle") from long distractor texts (the "haystack"), has been widely adopted to evaluate long-context language models (LMs). However, this simple retrieval-based test is indicative of only a superficial form of long-context understanding. To provide a more comprehensive evaluation of long-context LMs, we create a new synthetic benchmark RULER with flexible configurations for customized sequence length and task complexity. RULER expands upon the vanilla NIAH test to encompass variations with diverse types and quantities of needles. Moreover, RULER introduces new task categories multi-hop tracing and aggregation to test behaviors beyond searching from context. We evaluate 17 long-context LMs with 13 representative tasks in RULER. Despite achieving nearly perfect accuracy in the vanilla NIAH test, almost all models exhibit large performance drops as the context length increases. While these models all claim context sizes of 32K tokens or greater, only half of them can maintain satisfactory performance at the length of 32K. Our analysis of Yi-34B, which supports context length of 200K, reveals large room for improvement as we increase input length and task complexity. We open source RULER to spur comprehensive evaluation of long-context LMs.
hub tools
citation-role summary
background 1
citation-polarity summary
claims ledger
- abstract The needle-in-a-haystack (NIAH) test, which examines the ability to retrieve a piece of information (the "needle") from long distractor texts (the "haystack"), has been widely adopted to evaluate long-context language models (LMs). However, this simple retrieval-based test is indicative of only a superficial form of long-context understanding. To provide a more comprehensive evaluation of long-context LMs, we create a new synthetic benchmark RULER with flexible configurations for customized sequence length and task complexity. RULER expands upon the vanilla NIAH test to encompass variations wi
co-cited works
roles
background 1polarities
background 1representative citing papers
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
All tested LLM memory systems fail at dependency reasoning in multi-entity evolving scenarios, with only an expensive file-based setup showing partial recovery.
ProactBench measures LLM conversational proactivity in three phases using 198 multi-agent dialogues and finds recovery behavior hard to predict from existing benchmarks.
VORT assigns learnable fractional orders to tokens and approximates their power-law retention kernels via sum-of-exponentials for efficient long-range dependency modeling in transformers.
A new evaluation protocol shows agent memory reliability degrades variably with added irrelevant sessions depending on agent, memory interface, and scale.
LLM information retrieval shows a U-shaped performance drop as words are fragmented by inserted whitespace, attributed to a disordered transition between word-level and character-level processing modes.
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
HUGO-CS is a 4,383-experiment cold-spray dataset extracted from literature via a new hybrid LLM-manual framework that is 30 times larger than prior collections and released with code.
TokenArena is a continuous benchmark for AI inference endpoints that measures output speed, time to first token, blended price, effective context, quality, and modeled energy to produce composites of joules per correct answer, dollars per correct answer, and endpoint fidelity.
Stealth Pretraining Seeding plants persistent unsafe behaviors in LLMs via diffuse poisoned web content that activates on precise triggers and evades standard evaluation.
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
An agentic architecture with multimodal screening, a five-agent jury, meta-synthesis, and source attribution protocol detects biases in Romanian history textbooks more accurately than zero-shot baselines, achieving 83.3% acceptable excerpts and human preference in 64.8% of blind comparisons.
Attention to goal tokens declines in multi-turn LLM interactions while residual representations often retain decodable goal information, and the gap between these predicts whether goal-conditioned behavior survives.
AB-Sparse adaptively allocates per-head block sizes for sparse attention, adds lossless centroid quantization and custom variable-block GPU kernels, and reports up to 5.43% accuracy gain over fixed-block baselines with no throughput loss.
EXACT re-allocates training supervision by inverse frequency of long effective-context targets, improving NoLiMa and RULER scores by 5-18 points on Qwen and LLaMA models without degrading standard QA or reasoning.
GAPE augments RoPE with query- and key-dependent gates to stabilize attention and improve long-context performance in language models.
FocuSFT uses an inner optimization loop to adapt fast-weight parameters into a parametric memory that sharpens attention on relevant content, then conditions outer-loop supervised fine-tuning on this representation, yielding gains on long-context benchmarks.
KV-RM regularizes KV-cache movement in static-graph LLM serving via block paging and merge-staged transport to improve throughput, tail latency, and memory use for variable-length decoding.
ReST-KV formulates KV eviction as layer-wise output reconstruction optimization with spatial-temporal smoothing, outperforming baselines by 2.58% on LongBench and 15.2% on RULER while cutting decoding latency by 10.61x at 128k context.
Slipstream uses asynchronous compaction with trajectory-grounded judge validation to improve long-horizon agent accuracy by up to 8.8 percentage points and reduce latency by up to 39.7%.
RDKV derives per-token and per-channel weights from attention distortion, then uses reverse water-filling to assign bit-widths from full precision to zero after prefilling, recovering 97.81% accuracy with 2.48% cache retention on LongBench.
LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.
LLMs exhibit the Position Curse, with backward position retrieval in lists lagging far behind forward retrieval, showing only partial gains from PosBench fine-tuning.
citing papers explorer
-
MedMemoryBench: Benchmarking Agent Memory in Personalized Healthcare
MedMemoryBench supplies a 2,000-session synthetic medical trajectory dataset and an evaluate-while-constructing streaming protocol to expose memory saturation and reasoning failures in current agent architectures for personalized healthcare.
-
LongMemEval-V2: Evaluating Long-Term Agent Memory Toward Experienced Colleagues
LongMemEval-V2 is a new benchmark where AgentRunbook-C reaches 72.5% accuracy on long-term agent memory tasks, beating RAG baselines at 48.5% and basic coding agents at 69.3%.
-
MEME: Multi-entity & Evolving Memory Evaluation
All tested LLM memory systems fail at dependency reasoning in multi-entity evolving scenarios, with only an expensive file-based setup showing partial recovery.
-
ProactBench: Beyond What The User Asked For
ProactBench measures LLM conversational proactivity in three phases using 198 multi-agent dialogues and finds recovery behavior hard to predict from existing benchmarks.
-
VORT: Adaptive Power-Law Memory for NLP Transformers
VORT assigns learnable fractional orders to tokens and approximates their power-law retention kernels via sum-of-exponentials for efficient long-range dependency modeling in transformers.
-
When Stored Evidence Stops Being Usable: Scale-Conditioned Evaluation of Agent Memory
A new evaluation protocol shows agent memory reliability degrades variably with added irrelevant sessions depending on agent, memory interface, and scale.
-
The Text Uncanny Valley: Non-Monotonic Performance Degradation in LLM Information Retrieval
LLM information retrieval shows a U-shaped performance drop as words are fragmented by inserted whitespace, attributed to a disordered transition between word-level and character-level processing modes.
-
SCOUT: Active Information Foraging for Long-Text Understanding with Decoupled Epistemic States
SCOUT achieves state-of-the-art long-text understanding with up to 8x lower token use by actively foraging for sparse query-relevant information and updating a compact provenance-grounded epistemic state.
-
HUGO-CS: A Hybrid-Labeled, Uncertainty-Aware, General-Purpose, Observational Dataset for Cold Spray
HUGO-CS is a 4,383-experiment cold-spray dataset extracted from literature via a new hybrid LLM-manual framework that is 30 times larger than prior collections and released with code.
-
Token Arena: A Continuous Benchmark Unifying Energy and Cognition in AI Inference
TokenArena is a continuous benchmark for AI inference endpoints that measures output speed, time to first token, blended price, effective context, quality, and modeled energy to produce composites of joules per correct answer, dollars per correct answer, and endpoint fidelity.
-
PermaFrost-Attack: Stealth Pretraining Seeding(SPS) for planting Logic Landmines During LLM Training
Stealth Pretraining Seeding plants persistent unsafe behaviors in LLMs via diffuse poisoned web content that activates on precise triggers and evades standard evaluation.
-
Preconditioned DeltaNet: Curvature-aware Sequence Modeling for Linear Recurrences
Preconditioned delta-rule models with a diagonal curvature approximation improve upon standard DeltaNet, GDN, and KDA by better approximating the test-time regression objective.
-
An Agentic Evaluation Architecture for Historical Bias Detection in Educational Textbooks
An agentic architecture with multimodal screening, a five-agent jury, meta-synthesis, and source attribution protocol detects biases in Romanian history textbooks more accurately than zero-shot baselines, achieving 83.3% acceptable excerpts and human preference in 64.8% of blind comparisons.
-
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
Attention to goal tokens declines in multi-turn LLM interactions while residual representations often retain decodable goal information, and the gap between these predicts whether goal-conditioned behavior survives.
-
AB-Sparse: Sparse Attention with Adaptive Block Size for Accurate and Efficient Long-Context Inference
AB-Sparse adaptively allocates per-head block sizes for sparse attention, adds lossless centroid quantization and custom variable-block GPU kernels, and reports up to 5.43% accuracy gain over fixed-block baselines with no throughput loss.
-
Where Does Long-Context Supervision Actually Go? Effective-Context Exposure Balancing
EXACT re-allocates training supervision by inverse frequency of long effective-context targets, improving NoLiMa and RULER scores by 5-18 points on Qwen and LLaMA models without degrading standard QA or reasoning.
-
Remember to Forget: Gated Adaptive Positional Encoding
GAPE augments RoPE with query- and key-dependent gates to stabilize attention and improve long-context performance in language models.
-
FocuSFT: Bilevel Optimization for Dilution-Aware Long-Context Fine-Tuning
FocuSFT uses an inner optimization loop to adapt fast-weight parameters into a parametric memory that sharpens attention on relevant content, then conditions outer-loop supervised fine-tuning on this representation, yielding gains on long-context benchmarks.
-
KV-RM: Regularizing KV-Cache Movement for Static-Graph LLM Serving
KV-RM regularizes KV-cache movement in static-graph LLM serving via block paging and merge-staged transport to improve throughput, tail latency, and memory use for variable-length decoding.
-
ReST-KV: Robust KV Cache Eviction with Layer-wise Output Reconstruction and Spatial-Temporal Smoothing
ReST-KV formulates KV eviction as layer-wise output reconstruction optimization with spatial-temporal smoothing, outperforming baselines by 2.58% on LongBench and 15.2% on RULER while cutting decoding latency by 10.61x at 128k context.
-
Slipstream: Trajectory-Grounded Compaction Validation for Long-Horizon Agents
Slipstream uses asynchronous compaction with trajectory-grounded judge validation to improve long-horizon agent accuracy by up to 8.8 percentage points and reduce latency by up to 39.7%.
-
RDKV: Rate-Distortion Bit Allocation for Joint Eviction and Quantization of the KV Cache
RDKV derives per-token and per-channel weights from attention distortion, then uses reverse water-filling to assign bit-widths from full precision to zero after prefilling, recovering 97.81% accuracy with 2.48% cache retention on LongBench.
-
Reformulating KV Cache Eviction Problem for Long-Context LLM Inference
LaProx reformulates KV cache eviction as an output-aware matrix approximation, enabling a unified global token selection strategy that preserves LLM performance at 5% cache size across long-context benchmarks.
-
The Position Curse: LLMs Struggle to Locate the Last Few Items in a List
LLMs exhibit the Position Curse, with backward position retrieval in lists lagging far behind forward retrieval, showing only partial gains from PosBench fine-tuning.
-
Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
Louver is a new index for LLM KV caches that guarantees zero false negatives for keys above a relevance threshold, runs faster than prior sparse and some dense attention methods, and integrates lightly into existing pipelines.
-
UniPrefill: Universal Long-Context Prefill Acceleration via Block-wise Dynamic Sparsification
UniPrefill accelerates LLM prefill via block-wise dynamic sparsification, achieving up to 2.1x TTFT speedup while supporting hybrid architectures and native vLLM continuous batching.
-
When Does Value-Aware KV Eviction Help? A Fixed-Contract Diagnostic for Non-Monotone Cache Compression
A fixed-contract probe shows value-aware KV eviction recovers needed evidence in 72.6% of accuracy-improving cases on LongBench but only 32.4% otherwise, suggesting an order of recover evidence, rank value, then preserve couplings.
-
Retrieval and Multi-Hop Reasoning in 1M-Token Context Windows: Evaluating LLMs on Classical Chinese Text
Frontier LLMs solve single-needle retrieval at 1M tokens on classical Chinese but show three distinct accuracy-decay patterns in three-hop reasoning between 256K and 1M tokens.
-
Long-Context Aware Upcycling: A New Frontier for Hybrid LLM Scaling
HyLo upcycles Transformer LLMs into hybrids with MLA and Mamba2/Gated DeltaNet blocks via staged training and distillation, extending context to 2M tokens and outperforming prior upcycled hybrids on long-context benchmarks.
-
Efficient Mixture-of-Experts LLM Inference with Apple Silicon NPUs
NPUMoE accelerates MoE LLM inference on Apple Silicon NPUs via offline-calibrated static expert tiers, grouped execution, and load-aware graph residency, delivering 1.32x-5.55x lower latency and 1.81x-7.37x better energy efficiency.
-
OPSDL: On-Policy Self-Distillation for Long-Context Language Models
OPSDL improves long-context LLM performance by having the model self-distill from its short-context capability using point-wise reverse KL divergence on generated tokens, outperforming SFT and DPO on benchmarks without harming short-context abilities.
-
Sketching the Readout of Large Language Models for Scalable Data Attribution and Valuation
RISE applies CountSketch to dual lexical and semantic channels derived from output-layer gradient outer products, cutting data attribution storage by up to 112x and enabling retrospective and prospective influence analysis on LLMs up to 32B parameters.
-
Accuracy Is Speed: Towards Long-Context-Aware Routing for Distributed LLM Serving
In long-context LLM serving, accuracy becomes speed via retry dynamics, and accuracy-aware routing reduces time-to-correct-answer.
-
Latent-Condensed Transformer for Efficient Long Context Modeling
Latent-Condensed Attention condenses context in MLA's latent space via query-aware semantic pooling and positional anchor selection, delivering up to 2.5x prefilling speedup and 90% KV cache reduction at 128K length with a length-independent error bound.
-
IceCache: Memory-efficient KV-cache Management for Long-Sequence LLMs
IceCache combines semantic token clustering with PagedAttention to keep only 25% of the KV cache tokens while retaining 99% accuracy on LongBench and matching or beating prior offloading methods in latency.
-
StructKV: Preserving the Structural Skeleton for Scalable Long-Context Inference
StructKV compresses LLM KV caches by tracking global in-degree centrality across network depth and dynamically selecting compression layers to preserve long-range dependencies better than local pruning methods.
-
In-Place Test-Time Training
In-Place TTT adapts LLM MLP projection matrices at test time with a next-token-aligned objective and chunk-wise updates, enabling better long-context performance as a drop-in enhancement.
-
Safety, Security, and Cognitive Risks in State-Space Models: A Systematic Threat Analysis with Spectral, Stateful, and Capacity Attacks
State-space models are vulnerable to three new attack types that corrupt state integrity, with experiments showing up to 156x output changes and 6x higher targeted corruption than random inputs.
-
Kimi Linear: An Expressive, Efficient Attention Architecture
Kimi Linear hybridizes linear attention with a new KDA module to beat full attention on tasks while slashing KV cache by 75% and speeding decoding up to 6x.
-
Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free
Applying a head-specific sigmoid gate after SDPA in LLMs boosts performance and stability by adding non-linearity and query-dependent sparse modulation while reducing attention sinks.
-
MemReread: Enhancing Agentic Long-Context Reasoning via Memory-Guided Rereading
MemReread improves agent long-context reasoning by triggering rereading on insufficient final memory to recover discarded indirect facts, outperforming baselines at linear complexity.
-
Instruction Adherence in Coding Agent Configuration Files: A Factorial Study of Four File-Structure Variables
A 1650-session factorial study found no measurable impact from config file size, instruction position, architecture, or conflicts on coding agent adherence, though compliance declined within sessions.
-
LensVLM: Selective Context Expansion for Compressed Visual Representation of Text
LensVLM trains VLMs to scan compressed rendered text images and selectively expand task-relevant regions, achieving 4.3x compression with near full-text accuracy and outperforming baselines up to 10.1x on text QA benchmarks.
-
MDN: Parallelizing Stepwise Momentum for Delta Linear Attention
MDN parallelizes stepwise momentum for delta linear attention using geometric reordering and dynamical systems analysis, yielding performance gains over Mamba2 and GDN on 400M and 1.3B models.
-
StreamIndex: Memory-Bounded Compressed Sparse Attention via Streaming Top-k
Chunked streaming top-k enables CSA indexer execution at 1M sequence length with 6.21 GB peak memory and >=0.998 recall on synthetic V4-shaped inputs.
-
Budget-Aware Routing for Long Clinical Text
RCD balances relevance, coverage, and diversity in a knapsack-constrained selection framework, with experiments showing that selector choice and budget level determine optimal unitization strategies on clinical datasets.
-
Caracal: Causal Architecture via Spectral Mixing
Caracal is a Fourier-based sequence mixing architecture that achieves causal autoregressive modeling with standard operators and competitive performance on long sequences.
-
SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference
SpikingBrain2.0 is a 5B hybrid spiking-Transformer that recovers most base model performance while delivering 10x TTFT speedup at 4M context and supporting over 10M tokens on limited GPUs via dual sparse attention and dual quantization paths.
-
FG$^2$-GDN: Enhancing Long-Context Gated Delta Networks with Doubly Fine-Grained Control
FG²-GDN replaces the scalar beta in the delta update with a channel-wise vector and decouples key/value scaling to improve recall over prior GDN and KDA models.
-
LongAct: Harnessing Intrinsic Activation Patterns for Long-Context Reinforcement Learning
LongAct uses saliency from high-magnitude activations to guide sparse weight updates in long-context RL, yielding about 8% gains on LongBench v2 across multiple algorithms.