AI Research Radar

Monkey See, Can Monkey Do? A Benchmark for Evaluating Robot Skill Learning by Observation

How Long Until Your Robot Ignores You? A Safety Benchmark for LLM Orchestrators in Human-Humanoid Collaboration

“We find that (1) model family determines the safety floor, as Claude and Gemini remain at or near zero violations while GPT-4o-mini commits up to 13 per session, (2) context management dissociates two failure axes, reducing mean behavioral issues by 42-57% for every cloud backend while nearly doubling GPT-4o-mini's violations (3.8 to 7.2 per session), and (3) proportional compliance, clamping movement speed to the rule-specified maximum rather than refusing, emerges consistently only in Gemini; the preliminary simulation layer reproduces the model ranking and the GPT-4o-mini failure-mode inversion.”

Q2D-Web

“Retaining a third of the corpus, selected by reciprocal rank fusion over pooled retriever runs, preserves the full-corpus model ranking under the combined judgments while raising absolute Recall@1000 only by 3 to 7 points.”

A Cost-Aware Agentic Architecture for NL-to-SQL over Nested Enterprise Schemas, with a New Benchmark

“On the DevRev NL2SQL benchmark the system attains 91.7% answer correctness, a margin of 54.6 percentage points over the next-best baseline; on the Spider 2.0 Snowflake public dataset, it is competitive with leading systems at a single-generation operating point.”

OpenDiscoveryTrace

“Pilot analysis on 363 LLM-judged trajectories reveals that process traces expose behavioral differences invisible to output-only evaluation: all three frontier models achieve comparable success rates (84--89%), yet Claude Opus 4.6 produces 30× more errors than GPT-5.4 (2.5 vs. 0.08 per trajectory, p < 0.0001, Cliff's \delta = 0.613), with qualitatively different error profiles---66.7% tool misuse for Claude versus 83.6% reasoning errors for GPT-5.4.”

Bait-and-Recover

“Across four open-weight models, our defense raises the minimum refusal rate against white-box edit searches from 16.25% to 71.75% under a strict behavior-preservation budget (KL <= 0.10), with negligible impact on general benchmarks.”

TrojanWorld

“Experiments with the TD-MPC2, DreamerV3, and R2-Dreamer systems across the DeepMind Control, MetaWorld, MyoSuite, and RoboDesk benchmarks show that under trigger activation, TrojanWorld achieves a target-action deviation as low as 0.026 while retaining at least 98.8% of the corresponding clean performance.”

The Profit Alignment Problem

“In 3,600 controlled trials across eight reasoning-capable LLMs, adding a profit mandate to otherwise identical prompts increases risk-dismissing judgments by 6.8 percentage points (p < 0.0001), suppresses board escalation recommendations by 13.9pp (p < 0.0001), and shifts severity assessments downward (p < 0.0001).”

TruthInsightBench

SenseNova-U1.5

AuK Technical Report

“Experiments demonstrate leading performance on zero-shot and instruction-controlled speech generation and general instruction-guided editing, while remaining competitive on signal-level restoration tasks.”

Harness-agnostic detection and immunization of reward hacking in self-evolving language models