• ContextPilot Lets Agents Restructure Context Proactively: It turns planning, long-term memory, and soft offloading into learnable operations, then trains critical editing decisions with fine-grained RL.

• ElephantBench Exposes Correct but One-Sided Answers: Even the best of 32 models recovered both sides of conflicting accounts on only 52.4% of questions.

• RCCA Assigns Rewards to Responsible Code: It raised MiniAppBench scores from 9.05 to 41.25 while separating formatting, runtime, and functional failures.

Also Notable

• Can Video Priors Reduce Labels for Geometry Learning? — The study applies structured knowledge and rich video-generation priors to joint depth and surface-normal estimation.
• Counterfactual Reasoning Moves Into Open-World Causal Chains. — The benchmark tests whether models propagate downstream effects after conditions change.
• Equivariant Twin Worlds Test Whether Evidence Supports an Answer. — The method offers a refusal criterion distinct from confidence estimation when evidence is insufficient.
• Interpretable SAE Features Strengthen Refusals Without Retraining. — REINS adjusts model behavior at inference time when handling harmful requests.
• Multi-Agent Failures Need Targeted Blame, Not Group Reflection. — Attribution identifies the responsible node and triggers focused collaborative correction.
• Camouflaged Poison Documents Bypass Obvious RAG Defenses. — CamoDocs shows why query keywords and visible triggers cannot secure retrieval systems alone.
• Faithful Outputs Can Hide Missing Tool Calls. — Dispatch-level instrumentation reveals silent failures caused by structured-output constraints.
• Model-Merge Bias Also Appears in Decoder-Consumed Representations. — DARTS calibrates merged representations from the decoder's perspective.
• Visual-First Retrieval Avoids OCR Costs and Chart Loss. — PULSAR targets frequently updated, visually dense enterprise documents such as presentations.
• Which Prosodic Patterns Transfer Across Languages? — A multilingual dubbing dataset compares pitch, energy, and timing to inform expressive speech translation.

Read the full edition →