LExGraph advances exploration memory
LExGraph organizes exploration dialogues into graphs for superior long-term memory.
Stories per day · 30 days
3 RSS
Relatedbenchmark1benchmarks1distillation1ensemble1generative-models1gflownets1graph1llm-agents1memory1partial-observability1reinforcement-learning1robotics1rule-drift1test-time-adaptation1
15 stories, newest first · one card per story
Stories tagged #exploration
Hierarchical Cooperative GFlowNets coordinate sampler exploration
A shared classifier partitions the search space so lower-ranked models cover regions higher-ranked ones miss.
ASTEROID distillation teaches in-context exploration under partial observability
Across 11 environments it reports about 2x returns, about 100x fewer interactions than RL, and +40% real-robot success.
AdaExploreBench tests LLM agents on exploration and rule drift
Across eight leading models, GPT-6 Sol reaches only 61.9% calibrated accuracy when rules stay hidden and can change.
Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR
EDEN adds anchored embedding noise to RLVR rollouts, improving exploration and solution coverage over GRPO.
Decoupling Exploration from Optimization in RLVR
Exploration-Distillation separates novelty search from RLVR optimization and beats DAPO on math benchmarks.
RoboQuest: Generalist Physical Agents that Search, Inspect and Test
RoboQuest finds frontier physical agents succeed on only 23% of exploration tasks.
When Do Intrinsic Rewards Lead to Exploration?
A formal criterion shows common intrinsic rewards can fail to produce optimally informative exploration.
DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation
DexPolicy anneals exploration for dexterous manipulation, raising target success for PPO, GRPO, and FPO.
ExplorationBench: Measuring AI Systems' Exploration in Verifiable Alien Worlds
ExplorationBench evaluates AI systems' scientific exploration in verifiable 'Alien Worlds' sandboxes where recall cannot solve tasks; top systems still stall or reverse gains.
Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL
ActObs adds observation-token supervision to SFT, yielding higher pass@k for Qwen3 agents after GRPO on Terminal-Bench 2.0 and code editing.
Dream-RSI: Recursive Self-Improvement through Evolving Worlds
Dream-RSI refines exploration policies by dreaming in replay simulators built from discovery history, cutting discovery costs across coding tasks.
Enabling Creative Exploration for Vibe Design Agents
Separating design-direction exploration from code generation via structured specifications broadens UI alternatives without destabilizing output.
MInTRL: Off-policy Intervention can boost On-policy RL
MInTRL injects sparse judge corrections into on-policy RL rollouts, expanding exploration beyond on-policy sampling while preserving learnability on math and code benchmarks.
Import AI 469: Science AI; RSI simulator; and Zuck's technological pessimism
New DiG-bench benchmark of 70 hidden-rule games shows only Opus 5 and Fable 5 solving the hardest tiers, probing AI discovery and creativity.
3