RESEARCH

51 articles

All TopicsResearchAI Agents News Analysis Benchmarks Evaluation AI Coding

LATEST

Your Agent Has a Five-Constraint Budget

Give an agent one instruction and it obeys. Give it eight and it obeys all of them about five percent of the time, no matter which frontier model you bought. The phase transition is measured, the constraints also die in compaction and handoff notes, and in security-critical code the failure ships as infrastructure. The fix is not a better prompt. It is a smaller simultaneous budget and a side channel for the rules that must survive.

August 31, 2026•10 min read

Read Article

New10 min read

The Response Looked Right. The Work Was Not Done.

Across three independent benchmarks this week, agents claimed completion they had not earned: 75.5 percent of non-passing Claude Code trajectories end in language that says done, high partial scores hide 0 to 4 percent real delivery, and answer-only evals count invalid traces as wins. The same week produced the fix: completion is becoming a certifiable artifact - a typed certificate bound to a replayable trace - and it works. Our bet: by end of 2027, 'done' stops being the model's claim and becomes a checked artifact in any consequence-bearing workflow.

Research Analysis AI Agents

New9 min read

The Quiet Tax on Your Cheap Agent Tier

Compression is the default answer to the agent bill, and a new three-model, eleven-method audit says the bill is the wrong place to look: quantized and pruned agents lose their head knowledge first, stay confidently wrong about what they lost, and hide subgroup preference flips behind flat bias scores. The same week, the serving side produced cost cuts that touch none of that. Our bet: cheapness comes from the cache before it comes from the weights.

Research Analysis AI Agents

10 min read

The Oracle Is Agreeing With Itself

A feedback-driven test-generation loop reported steady improvement. An audit found a single-reference oracle had inflated the measured gain by 9.46 to 14.85 points, independent resampling beat the evolution at equal budget, and a placebo arm erased the feedback benefit. The judge was never the only layer that lied - the reference underneath shares the disease. Independent verification is the only real verification.

Research Analysis AI Agents

11 min read

The Judge Is Now a System You Design

LLM judges flip 25 to 71 percent of their verdicts under pushback and 62 to 91 percent under a trainable persuader, model rankings reverse across token budgets, and a deliberating jury of cheap open-weight models beats frontier single judges at 8 to 15 percent of the cost. The single-judge era is over. Here is the design spec that replaces it.

Research Analysis AI Agents

9 min read

We Read DeepSeek Harness: What 453K Lines of Agent Runtime Actually Say

DeepSeek open-sourced its agent harness today. We cloned it and read the code: a 453K-line plugin runtime on a vendored Cordis fork, three patterns worth stealing, V4 line signals hiding in the model adapter, and a 3-line BENCHMARK.md from a lab that published zero eval claims.

News Research AI Agents

8 min read

Mendel Godel Machine: Why Self-Improving Coding Agents Need Lineage

A new August 2026 paper argues that coding agents improve faster when they compare attempts across tasks and lineages, not just retry one failed trajectory.

AI Agents AI Coding Research

11 min read

Skill Files Are the New Supply Chain Attack Surface

Adversarial skill files - folders of instructions agents load dynamically - exploit a mainstream enterprise coding agent in 95.5 to 96.1 percent of runs, while the agent recognizes danger 1.99 percent of the time. The skill folder is now a measured attack surface, and the defense is admission engineering, not better prompts.

Research Analysis AI Agents

7 min read

ACE vs ALTK-Evolve: How You Deliver Agent Memory Determines the Token Bill

ACE and IBM's ALTK-Evolve both turn agent trajectories into reusable lessons. The difference is delivery: one injects the whole playbook every step, the other calibrates. On AppWorld, calibration wins with the same accuracy at a fraction of the tokens.

News AI Agents Agent Memory

7 min read

Encrypted Chain-of-Thought Is Not Private: New Paper Decodes Reasoning Traces From Anthropic, OpenAI, and Google APIs

A new arXiv paper shows the encrypted reasoning blocks that Anthropic, OpenAI, and Google return to API clients can be replayed into weaker models from the same provider and transcribed verbatim. The authors decoded 315,320 blocks from public repositories and recovered 367 PII artifacts and 182 credentials.

News Security AI Models

6 min read

Stop Means Stop: New Paper Finds Agent Approval Gates and Cancellation Leak in Six Frameworks

A new arXiv paper probes six widely used open-source agent frameworks and finds the barrier semantics of approval gates, cancellation, and timeouts hold on none of them. A sibling branch can execute while the user is rejecting another one, and replay can double-execute. The fix is a verified external gate called SoundGate.

News AI Agents Security

6 min read

AgentChaos: Fault Injection Shows Agent Robustness Is a Systems Problem, Not a Model Problem

A new ASE 2026 framework injects server errors, truncated responses, and corrupted tool calls into live agent systems at the HTTP layer. Every system degrades, pass@1 drops up to 50 points, and the ranking stays the same no matter which LLM is behind it.

News AI Agents Reliability

7 min read

LivePlan: Monitoring and Corrective Steering for Coding Agents, Without the LLM Tax

A new arXiv paper builds a deterministic monitor on top of SWE-agent that watches long agent trajectories and only calls an advisor LLM when the run actually drifts. Resolution rates go up by up to 15.2 points at an extra $0.08 per instance, and the paper argues the expensive approach is re-planning from inside the loop.

News AI Agents Research

Showing 12 of 50 articles

Keep exploring Research

- Research Topic Hub - tools and guides for Research from the Developers Digest directory
- Tools Directory - dive deeper across the Developers Digest knowledge base
- Developers Digest on YouTube - video tutorials covering Research and more

Explore 921 topics

Browse All Topics

RESEARCH

Your Agent Has a Five-Constraint Budget

Keep exploring Research

Get Smarter About AI Dev

RESEARCH

Your Agent Has a Five-Constraint Budget

Keep exploring Research

Get Smarter About AI Dev