Gemini 3.7 Flash (API ID: gemini-3.7-flash): 1M input / 64k output context, input $0.75, output $3.75 per 1M tokens (promotional pricing through 2026-12-31, reverting to $1.50 / $7.50 — same as predecessor 3.6 Flash); DeepSWE v1.1 65.3% (prev 48.6%), AutomationBench 30.4% (prev 17.0%), FrontierCode 1.1 43.6%; beats Claude Sonnet 5 and GPT-5.6 Terra on multiple agentic/enterprise automation benchmarks
DeepSeek V4-Pro peak Output jumped from $0.87 to $3.96/1M tokens (↑355%), V4-Flash from $0.28 to $1.32 (↑371%), effective 2026-08-16 16:00 UTC. Off-peak rates are half of peak (peak hours: 01:00-04:00 and 06:00-10:00 UTC). Post-hike prices still undercut GPT-5.6 and Claude, but the low-cost moat has narrowed significantly.
AgenticSeek (a 26K-star local AI Agent project on GitHub) has its backend bound to 0.0.0.0:7777 by default with CORS wide open. Anyone who can reach that port can send unauthenticated requests to the /query endpoint, which drives the Agent's BashInterpreter to run arbitrary commands via shell=True, safety=False — full host-level RCE (CVE-2026-72776, CVSS 9.3). The project has patched the issue (defaulting to loopback binding and allowlist CORS), but unpatched deployments remain exposed.
GitHub account zellkernel submitted PRs to 23 AI/MCP/dev-tool projects within 74 minutes, injecting a MCP server called productivity-suite into their config files. The server initially offers harmless text formatting and summarization, but an internal counter flips tools/list and prompts/get into malicious instructions after three tool calls — directing the Agent to search for SSH keys, AWS credentials, shell history, and Kubernetes configs while hiding the activity from the user. All 23 PRs remain unmerged (19 closed, 4 open), but the malicious endpoint is still live. Defense: treat any change to an approved MCP server's tool definitions as a security event requiring re-approval, and block the known endpoints.
pbx-mcp is an MCP server that wraps Asterisk (AMI) and FreeSWITCH (ESL) behind one set of MCP tools. Install: npx -y pbx-mcp. It solves the problem of memorizing two command sets when operating two PBX systems, and prevents Agents from accidentally running state-changing commands.
SkillEvo replaces single-turn QA evaluation with multi-turn interaction feedback so skill evolution doesn't stall after the first round, outperforming self-reflection by 23 points; SkillShapley brings Shapley values to skill step attribution — 99 evaluations approximate the exact ranking, revealing that 'decision-bridging steps' are the high-value ones; MindMemOS unifies memory management with an entity-property-time structure, hitting 94% on LOCOMO and lifting SpreadsheetBench success rate by 9.2 percentage points through skill evolution
Harness-IF reveals Coding Agent instruction following is overestimated by 3.6-7.4 pp because things the model would do anyway are counted as compliance; SHE decomposes the harness into four safety components and auto-evolves from trajectory failures, cutting ASR by 3.1x while improving correctness; SBCO uses a decomposed verifier bank with text gradients for harness self-improvement, matching Gödel Machine at 4-5.5x lower compute on planning tasks
EvoGraph-Mem uses a failure-aware editable graph to let agent memory self-correct, preventing stale insights from poisoning decisions; MAP-Graph turns provenance tracking from post-hoc audit into real-time access control, achieving 95% success across 2,700 synthetic tasks; MaSRead shows multi-agent KV cache sharing is possible but requires content-addressed reading instead of positional addressing
Tool interface design boosts coding agent consistency by 4.7x while halving token usage; memory distillation lifts a 4B model's AppWorld accuracy by 27.2 percentage points to near-frontier level; institutional design experiments show that identical safety rules paired with different enforcement mechanisms yield violation rates ranging from 0% to 23%
Muscle Memory proposes 'compiled memory' over retrieval-based memory, winning 88.9% of personalization matchups across 90 scenarios; MoRSE uses role-subtask conditioned LoRA experts to significantly outperform prompt-only role differentiation in code generation; ASCon builds a unified failure attribution model, improving by 5.83%, 10.63%, and 14.73% across three attribution targets
Evo-Bench benchmarks nine models on self-improving harnesses — GPT-5.6 Sol tops at +16.6 but Office tasks barely move; MEGA uses a three-layer Wisdom Graph to make agent optimization infrastructure self-evolving, merging knowledge accumulation with optimization; SHE decomposes harnesses into four evolvable components that learn safety boundaries from failure trajectories, cutting ASR by 3.1x with cross-model transferability
OneDayAgent's decompose-remember-verify harness hits 0.821 new SOTA on AgentIF-OneDay and works unchanged across five backends; The Horizon Gap surveys 1,547 papers to find that six categories of long-horizon failure share a single structural pattern — outcome-only signals degrade as step count grows, driving the field toward denser process signals; Evo-Bench is the first benchmark for harness self-evolution — GPT-5.6 Sol peaks at +16.6 absolute gain, but Office tasks still need hand-crafted workflows
Memory Reward Inflation finds that self-improving agents' memory rewards self-inflate — wrong experiences grow more confident over time; LUCID boosts accuracy from 54.0% to 56.9% on BIRD. RoMeRL compresses memory state space with fixed-dimension semantic coordinates, cutting Cold-Q ratio by 80% and LLM calls by 21.1%. ToolLIFT abstracts tool trajectories into function-level workflow graphs, consistently outperforming existing methods on three OOD benchmarks
ToolLIFT lifts tool trajectories to function-level workflow graphs and consistently beats SOTA on three OOD benchmarks; SkillTV-Bench uses 681 cases to show skill-aware judge skills boost agent evaluation accuracy by 14.8pp; TRIO-20's prespecified equivalence study finds zero unauthorized calls from GPT-5.6 across 840 trajectories, but higher reasoning effort increases rule-probing rate by 14.3pp
VerMem's seven atomic memory operations plus dual verifiers lead all baselines by 5-8 points across five benchmarks; SafeCommit cuts unsafe action rate from 41.2% to 2.6% while maintaining 97.4% task completion; ToolLIFT abstracts tool trajectories into function-level workflow graphs, outperforming the strongest baseline by 3-5 points on OOD benchmarks
ToolLIFT abstracts tool trajectories into function-level workflow graphs, lifting OOD accuracy by 4+ points on average; HyperAgent builds tool-schema hypergraphs with deficit-oriented expansion, beating ReAct by 14.3 points on AppWorld with lower token cost; a multilingual multi-agent planning diagnosis finds that planning grounding failures rise with decreasing language resources, and the TART fix improves scores by 5.6 points on average
Three papers examining AI Agent capabilities and limits from different angles: AutoMem shows memory management is a learnable skill — optimizing memory alone lifts a 32B open-source model to top commercial model levels; Shadow Evaluation tests whether frontier Agents can do open-ended AI research using real NeurIPS submissions — the answer is no, Agents can engineer but cannot research; Adaptive Adversaries reveals that existing safety benchmarks severely underestimate threats — adding adaptive multi-turn attackers jumps ASR from 0–1% to 14%. Together, these three papers deliver a sobering lesson: know where Agents can automatically improve, where they cannot, and that your security testing is probably insufficient.
Three papers tackling multi-agent platform challenges from three angles: organizational design, security isolation, and user-level authorization. IMACS decomposes multi-agent systems into three independently swappable layers (organization, coordination, collaboration algorithm), letting framework designers mix and match agent roles and strategies like building blocks. APPA uses context branching to break the usability bottleneck of IFC (Information Flow Control), cutting prompt injection exfiltration rates from 31–50% down to 0–7% across 4 models. A UW survey of 21 agent authorization proposals finds that nearly all systems offer only developer-defined global policies — user-level personalized authorization is virtually absent. Together, the three papers outline the gaps agent platforms must close on the road from prototype to production.
Three papers tackle 'what goes wrong when agents hit production' from different angles: ProACT addresses when an agent should speak up in multi-user collaboration (an Agent UX design problem); the second uses real GitHub data to reveal that coding agents clash with their own PRs (a platform ops pain point); the third surveys five vulnerability classes of cyber-capable agents, using July 2026 HuggingFace/OpenAI incidents as case studies. Together, they form a crash course in post-deployment agent headaches.
Three papers probe the real-world limits of AI Agents from different angles: ORCA-bench drops LLM Agents into production SRE on-call for root cause analysis — the best model scores only 40%; AgentS4D reveals the safety blind spot of workspace agents — 66% of 'successful' runs still triggered dangerous behavior; a Context Files study finds that AGENTS.md / CLAUDE.md files show no measurable improvement in coding agent correctness across 288 controlled trials.