A sleep mechanism with N offline recurrent passes consolidates context into fast weights, improving performance on reasoning tasks where standard transformers fail.
Title resolution pending
13 Pith papers cite this work. Polarity classification is still indexing.
13
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
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%.
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
RATs agents generate and solve their own exploratory tasks during play, distill successful code into a skill library, and reuse it to improve held-out task performance by 20.6 and 17.0 points on two benchmarks.
Language models can use a two-stage sleep process of upward distillation for memory consolidation and RL-based dreaming for unsupervised self-improvement to enable continual learning.
ProAct uses idle compute to anticipate user needs via dialogue history and memory, achieving 14.8% fewer turns, 11.7% less user effort, and 28.1% fewer hallucinations than reactive baselines on the new ProActEval benchmark.
Auto-Dreamer trains an offline memory consolidator via GRPO on agent performance to abstract cross-session patterns, outperforming baselines by 7 points on ScienceWorld with 12x smaller memory and generalizing to ALFWorld and WebArena.
Shorter LLM response latencies reduce perceived output thoughtfulness and usefulness, while task type affects prompting frequency independently of latency.
RHO is a self-supervised technique that selects challenging past tasks, re-solves them, and uses self-preference to update an agent's harness, raising SWE-Bench Pro pass rate from 59% to 78% without external labels.
BALAR is a task-agnostic Bayesian loop that maintains structured beliefs over latent states, selects questions via expected mutual information, and expands its state space when needed, delivering 14.6-38.5% accuracy gains over baselines on detective, puzzle, and clinical diagnosis benchmarks.
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
citing papers explorer
-
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents
IdleSpec improves LLM agent accuracy by generating and aggregating speculative plans during idle time between tool calls and observations using complementary drafting strategies.
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
Evolving Agents in the Dark: Retrospective Harness Optimization via Self-Preference
RHO is a self-supervised technique that selects challenging past tasks, re-solves them, and uses self-preference to update an agent's harness, raising SWE-Bench Pro pass rate from 59% to 78% without external labels.
-
BALAR : A Bayesian Agentic Loop for Active Reasoning
BALAR is a task-agnostic Bayesian loop that maintains structured beliefs over latent states, selects questions via expected mutual information, and expands its state space when needed, delivering 14.6-38.5% accuracy gains over baselines on detective, puzzle, and clinical diagnosis benchmarks.