LifeSide is a new benchmark that evaluates AI agents on multi-session Memory-Emotion-Environment loops via simulated user profiles and event trajectories, revealing that models saturating existing memory tests fail at long-horizon user understanding.
hub
and Yoon, Seunghyun and Sch
17 Pith papers cite this work. Polarity classification is still indexing.
17
Pith papers citing it
hub tools
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
ContextEcho benchmark shows persona drift occurs across 23 frontier models in long agentic-coding sessions, is not reliably reset by compaction, and can be restored by single-shot anchors with mode-dependent effects.
Audits reveal no reasoning benchmark controls position/filler/length jointly; CRE shows LLMs drop up to 88pp on middle-position tasks at 64K context, with diagnostic probe supporting positional cause.
VAEX-BENCH shows state-of-the-art MLLMs perform substantially worse on abstractive spatiotemporal reasoning tasks than on matched extractive tasks in video understanding.
KForge uses dual LLM agents for cross-platform kernel generation, reporting 2.12% throughput gain on NVIDIA B200 vs TensorRT-LLM and 5.13x geometric mean speedup on Intel Arc B580 vs PyTorch on 37 workloads.
A matched-control protocol on SQuAD recovers 4.5-6 EM points and 0.057-0.068 F1 in two small models by swapping hard distractors for easier ones, isolating semantic competition from context length.
Parallel compaction for LLM agent context management provides predictable volume control and reduces wall time versus sequential baselines on HotpotQA and LoCoMo.
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.
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%.
Attention-based models can retrieve evidence intrinsically by using decoder attention to score and reuse their own pre-encoded chunks, outperforming separate retrieval pipelines on QA benchmarks.
EASE-TTT creates a soft attention target from evidence chunks to guide query-side test-time adaptation, yielding higher macro-average scores than full-context, retrieval-only, and standard qTTT baselines on six LongBench QA tasks.
Reasoning in large output spaces proceeds via shortlisting then fine-grained reasoning; this characterization enables a mechanistic distillation strategy that outperforms standard distillation.
Tool Attention cuts tool-related tokens by 95% and raises context utilization from 24% to 91% in a 120-tool simulation via dynamic gating and lazy loading.
Expert interviews demonstrate that context in generative AI workplace use collapses or rots over time, limiting tool effectiveness and revealing pitfalls in computational context approaches.
MemOCR renders structured memory as images with adaptive visual density to improve long-horizon reasoning under tight context budgets.
MiMo-V2-Flash is a 309B/15B MoE model trained on 27T tokens with hybrid attention and multi-teacher on-policy distillation that matches larger models like DeepSeek-V3.2 while enabling 2.6x faster decoding via repurposed MTP layers.
citing papers explorer
No citing papers match the current filters.